diff --git a/server/poetry.lock b/server/poetry.lock
index 1930cbeca..e664eb00c 100644
--- a/server/poetry.lock
+++ b/server/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "accelerate"
@@ -6,6 +6,8 @@ version = "0.24.1"
 description = "Accelerate"
 optional = true
 python-versions = ">=3.8.0"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\""
 files = [
     {file = "accelerate-0.24.1-py3-none-any.whl", hash = "sha256:866dec394da60e8da964be212379d8cf6cc0d0e5e28a7c0d7e09507715d21c61"},
     {file = "accelerate-0.24.1.tar.gz", hash = "sha256:85ab2aeb4d06194b75113339f81b7d650523414a82c9e91b2912a655f53dfa8e"},
@@ -35,6 +37,7 @@ version = "2.5.0"
 description = "Happy Eyeballs for asyncio"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "aiohappyeyeballs-2.5.0-py3-none-any.whl", hash = "sha256:0850b580748c7071db98bffff6d4c94028d0d3035acc20fd721a0ce7e8cac35d"},
     {file = "aiohappyeyeballs-2.5.0.tar.gz", hash = "sha256:18fde6204a76deeabc97c48bdd01d5801cfda5d6b9c8bbeb1aaaee9d648ca191"},
@@ -46,6 +49,7 @@ version = "3.10.11"
 description = "Async http client/server framework (asyncio)"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "aiohttp-3.10.11-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5077b1a5f40ffa3ba1f40d537d3bec4383988ee51fbba6b74aa8fb1bc466599e"},
     {file = "aiohttp-3.10.11-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8d6a14a4d93b5b3c2891fca94fa9d41b2322a68194422bef0dd5ec1e57d7d298"},
@@ -150,7 +154,7 @@ multidict = ">=4.5,<7.0"
 yarl = ">=1.12.0,<2.0"
 
 [package.extras]
-speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
+speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 
 [[package]]
 name = "aiosignal"
@@ -158,6 +162,7 @@ version = "1.3.2"
 description = "aiosignal: a list of registered asynchronous callbacks"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "aiosignal-1.3.2-py2.py3-none-any.whl", hash = "sha256:45cde58e409a301715980c2b01d0c28bdde3770d8290b5eb2173759d9acb31a5"},
     {file = "aiosignal-1.3.2.tar.gz", hash = "sha256:a8c255c66fafb1e499c9351d0bf32ff2d8a0321595ebac3b93713656d2436f54"},
@@ -172,6 +177,8 @@ version = "20250224"
 description = "Extensive database of location and timezone data for nearly every airport and landing strip in the world."
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "airportsdata-20250224-py3-none-any.whl", hash = "sha256:006128bca2cc1983dc5ed4fb1227e8df2289b5e95b8ab30d9bdd4eb7c6d2160d"},
     {file = "airportsdata-20250224.tar.gz", hash = "sha256:7f4538a613504444a13149be701aac5f9599b86da476d26b46aa24fd54714eda"},
@@ -183,6 +190,8 @@ version = "0.7.0"
 description = "Reusable constraint types to use with typing.Annotated"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53"},
     {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"},
@@ -194,6 +203,8 @@ version = "5.0.1"
 description = "Timeout context manager for asyncio programs"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "python_version <= \"3.10\""
 files = [
     {file = "async_timeout-5.0.1-py3-none-any.whl", hash = "sha256:39e3809566ff85354557ec2398b55e096c8364bacac9405a7a1fa429e77fe76c"},
     {file = "async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3"},
@@ -205,18 +216,19 @@ version = "25.1.0"
 description = "Classes Without Boilerplate"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "attrs-25.1.0-py3-none-any.whl", hash = "sha256:c75a69e28a550a7e93789579c22aa26b0f5b83b75dc4e08fe092980051e1090a"},
     {file = "attrs-25.1.0.tar.gz", hash = "sha256:1c97078a80c814273a76b2a298a932eb681c87415c11dee0a6921de7f1b02c3e"},
 ]
 
 [package.extras]
-benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
+cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
+dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
 docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
+tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
+tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\""]
 
 [[package]]
 name = "backoff"
@@ -224,6 +236,7 @@ version = "2.2.1"
 description = "Function decoration for backoff and retry"
 optional = false
 python-versions = ">=3.7,<4.0"
+groups = ["main"]
 files = [
     {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
     {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
@@ -235,6 +248,8 @@ version = "0.1.0.post1"
 description = "A light weight framework to generate high performance CUDA/HIP code for BLAS operators."
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "bitblas-0.1.0.post1-py3-none-manylinux1_x86_64.whl", hash = "sha256:5beaf38899671dc35da63ff31b8d7bea4d98a2c929a102fe40d2f3004cec391b"},
 ]
@@ -270,6 +285,8 @@ version = "0.43.3"
 description = "k-bit optimizers and matrix multiplication routines."
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"bnb\""
 files = [
     {file = "bitsandbytes-0.43.3-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:cc99507c352be0715098b2c7577b690dd158972dc4ea10c7495bac104c7c79f0"},
     {file = "bitsandbytes-0.43.3-py3-none-win_amd64.whl", hash = "sha256:257f6552f2144748a84e6c44e1f7a98f3da888f675ed74e18fd7f7eb13c6cafa"},
@@ -289,6 +306,7 @@ version = "1.37.8"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "boto3-1.37.8-py3-none-any.whl", hash = "sha256:b9f506e08c9f54687d6c073ef1c550a24a62cc2d1e0bc7cda9f13112a38818bf"},
     {file = "boto3-1.37.8.tar.gz", hash = "sha256:9448f4a079189e19c3253cfdc5b8ef6dc51a3b82431e8347a51f4c1b2d9dab42"},
@@ -308,6 +326,7 @@ version = "1.37.8"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "botocore-1.37.8-py3-none-any.whl", hash = "sha256:a6c94f33de12f4b10b10684019e554c980469b8394c6d82448a738cbd8452cef"},
     {file = "botocore-1.37.8.tar.gz", hash = "sha256:b5825e08dd3e25642aa22a0d7d92bf81fef1ef857117e4155f923bbccf5aba63"},
@@ -330,6 +349,7 @@ version = "2025.1.31"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.6"
+groups = ["main"]
 files = [
     {file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"},
     {file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"},
@@ -341,6 +361,8 @@ version = "1.17.1"
 description = "Foreign Function Interface for Python calling C code."
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "cffi-1.17.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:df8b1c11f177bc2313ec4b2d46baec87a5f3e71fc8b45dab2ee7cae86d9aba14"},
     {file = "cffi-1.17.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8f2cdc858323644ab277e9bb925ad72ae0e67f69e804f4898c070998d50b1a67"},
@@ -420,6 +442,7 @@ version = "3.4.1"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "charset_normalizer-3.4.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:91b36a978b5ae0ee86c394f5a54d6ef44db1de0815eb43de826d41d21e4af3de"},
     {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7461baadb4dc00fd9e0acbe254e3d7d2112e7f92ced2adc96e54ef6501c5f176"},
@@ -521,6 +544,7 @@ version = "8.1.8"
 description = "Composable command line interface toolkit"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2"},
     {file = "click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a"},
@@ -535,6 +559,8 @@ version = "3.1.1"
 description = "Pickler class to extend the standard pickle.Pickler functionality"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\" or extra == \"outlines\""
 files = [
     {file = "cloudpickle-3.1.1-py3-none-any.whl", hash = "sha256:c8c5a44295039331ee9dad40ba100a9c7297b6f988e50e87ccdf3765a668350e"},
     {file = "cloudpickle-3.1.1.tar.gz", hash = "sha256:b216fa8ae4019d5482a8ac3c95d8f6346115d8835911fd4aefd1a445e4242c64"},
@@ -546,10 +572,12 @@ version = "0.4.6"
 description = "Cross-platform colored terminal text."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+groups = ["main", "dev"]
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
+markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\"", dev = "sys_platform == \"win32\""}
 
 [[package]]
 name = "cpplint"
@@ -557,6 +585,8 @@ version = "2.0.0"
 description = "Automated checker to ensure C++ files follow Google's style guide"
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "cpplint-2.0.0-py3-none-any.whl", hash = "sha256:f418e1d76a14b44e0757b39faa8bd47543e352ced697afd35a598a0114aec69f"},
     {file = "cpplint-2.0.0.tar.gz", hash = "sha256:330daf6bf9a9006b9161af6693661df8f8373d54b2ea6527cd515a8e61d41abb"},
@@ -572,6 +602,8 @@ version = "3.0.12"
 description = "The Cython compiler for writing C extensions in the Python language."
 optional = true
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "Cython-3.0.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ba67eee9413b66dd9fbacd33f0bc2e028a2a120991d77b5fd4b19d0b1e4039b9"},
     {file = "Cython-3.0.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bee2717e5b5f7d966d0c6e27d2efe3698c357aa4d61bb3201997c7a4f9fe485a"},
@@ -645,6 +677,8 @@ version = "2.14.4"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = true
 python-versions = ">=3.8.0"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "datasets-2.14.4-py3-none-any.whl", hash = "sha256:29336bd316a7d827ccd4da2236596279b20ca2ac78f64c04c9483da7cbc2459b"},
     {file = "datasets-2.14.4.tar.gz", hash = "sha256:ef29c2b5841de488cd343cfc26ab979bff77efa4d2285af51f1ad7db5c46a83b"},
@@ -669,15 +703,15 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0,<2.44.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "black (>=23.1,<24.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "pyyaml (>=5.3.1)", "rarfile (>=4.0)", "ruff (>=0.0.241)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"]
-docs = ["s3fs", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos", "torch", "transformers"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0) ; python_version < \"3.10\"", "black (>=23.1,<24.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "pyyaml (>=5.3.1)", "rarfile (>=4.0)", "ruff (>=0.0.241)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1) ; sys_platform != \"darwin\" or platform_machine != \"arm64\"", "tensorflow (>=2.3,!=2.6.0,!=2.6.1) ; sys_platform != \"darwin\" or platform_machine != \"arm64\"", "tensorflow-macos ; sys_platform == \"darwin\" and platform_machine == \"arm64\"", "tiktoken", "torch", "transformers", "zstandard"]
+docs = ["s3fs", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1) ; sys_platform != \"darwin\" or platform_machine != \"arm64\"", "tensorflow-macos ; sys_platform == \"darwin\" and platform_machine == \"arm64\"", "torch", "transformers"]
 jax = ["jax (>=0.2.8,!=0.3.2,<=0.3.25)", "jaxlib (>=0.1.65,<=0.3.25)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["black (>=23.1,<24.0)", "pyyaml (>=5.3.1)", "ruff (>=0.0.241)"]
 s3 = ["s3fs"]
-tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos"]
+tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1) ; sys_platform != \"darwin\" or platform_machine != \"arm64\"", "tensorflow-macos ; sys_platform == \"darwin\" and platform_machine == \"arm64\""]
 tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0) ; python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1) ; sys_platform != \"darwin\" or platform_machine != \"arm64\"", "tensorflow-macos ; sys_platform == \"darwin\" and platform_machine == \"arm64\"", "tiktoken", "torch", "transformers", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -687,6 +721,8 @@ version = "5.2.1"
 description = "Decorators for Humans"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "decorator-5.2.1-py3-none-any.whl", hash = "sha256:d316bb415a2d9e2d2b3abcc4084c6502fc09240e292cd76a76afc106a1c8e04a"},
     {file = "decorator-5.2.1.tar.gz", hash = "sha256:65f266143752f734b0a7cc83c46f4618af75b8c5911b00ccb61d0ac9b6da0360"},
@@ -698,6 +734,7 @@ version = "1.2.18"
 description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
+groups = ["main"]
 files = [
     {file = "Deprecated-1.2.18-py2.py3-none-any.whl", hash = "sha256:bd5011788200372a32418f888e326a09ff80d0214bd961147cfed01b5c018eec"},
     {file = "deprecated-1.2.18.tar.gz", hash = "sha256:422b6f6d859da6f2ef57857761bfb392480502a64c3028ca9bbe86085d72115d"},
@@ -707,7 +744,7 @@ files = [
 wrapt = ">=1.10,<2"
 
 [package.extras]
-dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "setuptools", "tox"]
+dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "setuptools ; python_version >= \"3.12\"", "tox"]
 
 [[package]]
 name = "dill"
@@ -715,6 +752,8 @@ version = "0.3.7"
 description = "serialize all of Python"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "dill-0.3.7-py3-none-any.whl", hash = "sha256:76b122c08ef4ce2eedcd4d1abd8e641114bfc6c2867f49f3c41facf65bf19f5e"},
     {file = "dill-0.3.7.tar.gz", hash = "sha256:cc1c8b182eb3013e24bd475ff2e9295af86c1a38eb1aff128dac8962a9ce3c03"},
@@ -729,6 +768,8 @@ version = "5.6.3"
 description = "Disk Cache -- Disk and file backed persistent cache."
 optional = true
 python-versions = ">=3"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19"},
     {file = "diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc"},
@@ -740,6 +781,8 @@ version = "0.21.2"
 description = "Docutils -- Python Documentation Utilities"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "docutils-0.21.2-py3-none-any.whl", hash = "sha256:dafca5b9e384f0e419294eb4d2ff9fa826435bf15f15b7bd45723e8ad76811b2"},
     {file = "docutils-0.21.2.tar.gz", hash = "sha256:3a6b18732edf182daa3cd12775bbb338cf5691468f91eeeb109deff6ebfa986f"},
@@ -751,6 +794,8 @@ version = "0.0.0.dev2"
 description = "A small package of basic data structures and algorithms"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "dtlib-0.0.0.dev2-py3-none-any.whl", hash = "sha256:c95982fea15b7bcdcf7d53cd4a0183f6f88ce2176dda90e087320786c8f45fa1"},
     {file = "dtlib-0.0.0.dev2.tar.gz", hash = "sha256:185fe92d8dd872fce8a9c08c8f23cb2dbfb1f2f75e931f179a3cf8c12fa19171"},
@@ -762,6 +807,7 @@ version = "0.6.1"
 description = "A new flavour of deep learning operations"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "einops-0.6.1-py3-none-any.whl", hash = "sha256:99149e46cc808956b174932fe563d920db4d6e5dadb8c6ecdaa7483b7ef7cfc3"},
     {file = "einops-0.6.1.tar.gz", hash = "sha256:f95f8d00f4ded90dbc4b19b6f98b177332614b0357dde66997f3ae5d474dc8c8"},
@@ -773,6 +819,8 @@ version = "1.2.2"
 description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev"]
+markers = "python_version <= \"3.10\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -787,6 +835,8 @@ version = "2.1.1"
 description = "execnet: rapid multi-Python deployment"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "execnet-2.1.1-py3-none-any.whl", hash = "sha256:26dee51f1b80cebd6d0ca8e74dd8745419761d3bef34163928cbebbdc4749fdc"},
     {file = "execnet-2.1.1.tar.gz", hash = "sha256:5189b52c6121c24feae288166ab41b32549c7e2348652736540b9e6e7d4e72e3"},
@@ -801,6 +851,7 @@ version = "3.17.0"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "filelock-3.17.0-py3-none-any.whl", hash = "sha256:533dc2f7ba78dc2f0f531fc6c4940addf7b70a481e269a5a3b93be94ffbe8338"},
     {file = "filelock-3.17.0.tar.gz", hash = "sha256:ee4e77401ef576ebb38cd7f13b9b28893194acc20a8e68e18730ba9c0e54660e"},
@@ -809,7 +860,7 @@ files = [
 [package.extras]
 docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"]
-typing = ["typing-extensions (>=4.12.2)"]
+typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
 
 [[package]]
 name = "frozenlist"
@@ -817,6 +868,7 @@ version = "1.5.0"
 description = "A list-like structure which implements collections.abc.MutableSequence"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "frozenlist-1.5.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5b6a66c18b5b9dd261ca98dffcb826a525334b2f29e7caa54e182255c5f6a65a"},
     {file = "frozenlist-1.5.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d1b3eb7b05ea246510b43a7e53ed1653e55c2121019a97e60cad7efb881a97bb"},
@@ -918,6 +970,7 @@ version = "2025.2.0"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "fsspec-2025.2.0-py3-none-any.whl", hash = "sha256:9de2ad9ce1f85e1931858535bc882543171d197001a0a5eb2ddc04f1781ab95b"},
     {file = "fsspec-2025.2.0.tar.gz", hash = "sha256:1c24b16eaa0a1798afa0337aa0db9b256718ab2a89c425371f5628d22c3b6afd"},
@@ -960,6 +1013,8 @@ version = "1.3.0"
 description = "GenSON is a powerful, user-friendly JSON Schema generator."
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "genson-1.3.0-py3-none-any.whl", hash = "sha256:468feccd00274cc7e4c09e84b08704270ba8d95232aa280f65b986139cec67f7"},
     {file = "genson-1.3.0.tar.gz", hash = "sha256:e02db9ac2e3fd29e65b5286f7135762e2cd8a986537c075b06fc5f1517308e37"},
@@ -971,6 +1026,7 @@ version = "1.69.1"
 description = "Common protobufs used in Google APIs"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "googleapis_common_protos-1.69.1-py2.py3-none-any.whl", hash = "sha256:4077f27a6900d5946ee5a369fab9c8ded4c0ef1c6e880458ea2f70c14f7b70d5"},
     {file = "googleapis_common_protos-1.69.1.tar.gz", hash = "sha256:e20d2d8dda87da6fe7340afbbdf4f0bcb4c8fae7e6cadf55926c31f946b0b9b1"},
@@ -988,6 +1044,7 @@ version = "0.15.4"
 description = "Simplifies gRPC interceptors"
 optional = false
 python-versions = ">=3.7,<4.0"
+groups = ["main"]
 files = [
     {file = "grpc-interceptor-0.15.4.tar.gz", hash = "sha256:1f45c0bcb58b6f332f37c637632247c9b02bc6af0fdceb7ba7ce8d2ebbfb0926"},
     {file = "grpc_interceptor-0.15.4-py3-none-any.whl", hash = "sha256:0035f33228693ed3767ee49d937bac424318db173fef4d2d0170b3215f254d9d"},
@@ -1005,6 +1062,7 @@ version = "1.70.0"
 description = "HTTP/2-based RPC framework"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev"]
 files = [
     {file = "grpcio-1.70.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:95469d1977429f45fe7df441f586521361e235982a0b39e33841549143ae2851"},
     {file = "grpcio-1.70.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:ed9718f17fbdb472e33b869c77a16d0b55e166b100ec57b016dc7de9c8d236bf"},
@@ -1072,6 +1130,7 @@ version = "1.62.3"
 description = "Standard Protobuf Reflection Service for gRPC"
 optional = false
 python-versions = ">=3.6"
+groups = ["main"]
 files = [
     {file = "grpcio-reflection-1.62.3.tar.gz", hash = "sha256:cb84682933c400bddf94dd94f928d1c6570f500b6dd255973d4bfb495b82585f"},
     {file = "grpcio_reflection-1.62.3-py3-none-any.whl", hash = "sha256:a48ef37df81a3bada78261fc92ef382f061112f989d1312398b945cc69838b9c"},
@@ -1087,6 +1146,7 @@ version = "1.62.3"
 description = "Status proto mapping for gRPC"
 optional = false
 python-versions = ">=3.6"
+groups = ["main"]
 files = [
     {file = "grpcio-status-1.62.3.tar.gz", hash = "sha256:289bdd7b2459794a12cf95dc0cb727bd4a1742c37bd823f760236c937e53a485"},
     {file = "grpcio_status-1.62.3-py3-none-any.whl", hash = "sha256:f9049b762ba8de6b1086789d8315846e094edac2c50beaf462338b301a8fd4b8"},
@@ -1103,6 +1163,7 @@ version = "1.62.3"
 description = "Protobuf code generator for gRPC"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "grpcio-tools-1.62.3.tar.gz", hash = "sha256:7c7136015c3d62c3eef493efabaf9e3380e3e66d24ee8e94c01cb71377f57833"},
     {file = "grpcio_tools-1.62.3-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:2f968b049c2849540751ec2100ab05e8086c24bead769ca734fdab58698408c1"},
@@ -1165,6 +1226,7 @@ version = "0.1.9"
 description = "Speed up file transfers with the Hugging Face Hub."
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "hf_transfer-0.1.9-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:6e94e8822da79573c9b6ae4d6b2f847c59a7a06c5327d7db20751b68538dc4f6"},
     {file = "hf_transfer-0.1.9-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:3ebc4ab9023414880c8b1d3c38174d1c9989eb5022d37e814fa91a3060123eb0"},
@@ -1199,6 +1261,8 @@ version = "0.1.8"
 description = "Half-Quadratic Quantization (HQQ)"
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "hqq-0.1.8.tar.gz", hash = "sha256:c09251f74b17c4aec4653f67c690e4cb33ffff55fd0c69220233b4c99b88b135"},
 ]
@@ -1219,6 +1283,7 @@ version = "0.26.5"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
+groups = ["main"]
 files = [
     {file = "huggingface_hub-0.26.5-py3-none-any.whl", hash = "sha256:fb7386090bbe892072e64b85f7c4479fd2d65eea5f2543327c970d5169e83924"},
     {file = "huggingface_hub-0.26.5.tar.gz", hash = "sha256:1008bd18f60bfb65e8dbc0a97249beeeaa8c99d3c2fa649354df9fa5a13ed83b"},
@@ -1253,6 +1318,7 @@ version = "3.10"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.6"
+groups = ["main"]
 files = [
     {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
     {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
@@ -1267,6 +1333,7 @@ version = "6.11.0"
 description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "importlib_metadata-6.11.0-py3-none-any.whl", hash = "sha256:f0afba6205ad8f8947c7d338b5342d5db2afbfd82f9cbef7879a9539cc12eb9b"},
     {file = "importlib_metadata-6.11.0.tar.gz", hash = "sha256:1231cf92d825c9e03cfc4da076a16de6422c863558229ea0b22b675657463443"},
@@ -1278,7 +1345,7 @@ zipp = ">=0.5"
 [package.extras]
 docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-testing = ["flufl.flake8", "importlib-resources (>=1.3)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy (>=0.9.1)", "pytest-perf (>=0.9.2)", "pytest-ruff"]
+testing = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "packaging", "pyfakefs", "pytest (>=6)", "pytest-black (>=0.3.7) ; platform_python_implementation != \"PyPy\"", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy (>=0.9.1) ; platform_python_implementation != \"PyPy\"", "pytest-perf (>=0.9.2)", "pytest-ruff"]
 
 [[package]]
 name = "iniconfig"
@@ -1286,6 +1353,7 @@ version = "2.0.0"
 description = "brain-dead simple config-ini parsing"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev"]
 files = [
     {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
@@ -1297,6 +1365,8 @@ version = "0.3.3"
 description = "a regex intersection checker"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "interegular-0.3.3-py37-none-any.whl", hash = "sha256:b0c07007d48c89d6d19f7204972d369b2a77222722e126b6aa63aa721dc3b19c"},
     {file = "interegular-0.3.3.tar.gz", hash = "sha256:d9b697b21b34884711399ba0f0376914b81899ce670032486d0d048344a76600"},
@@ -1308,6 +1378,8 @@ version = "3.1.6"
 description = "A very fast and expressive template engine."
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
 files = [
     {file = "jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67"},
     {file = "jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d"},
@@ -1325,6 +1397,7 @@ version = "1.0.1"
 description = "JSON Matching Expressions"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980"},
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
@@ -1336,6 +1409,8 @@ version = "4.23.0"
 description = "An implementation of JSON Schema validation for Python"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "jsonschema-4.23.0-py3-none-any.whl", hash = "sha256:fbadb6f8b144a8f8cf9f0b89ba94501d143e50411a1278633f56a7acf7fd5566"},
     {file = "jsonschema-4.23.0.tar.gz", hash = "sha256:d71497fef26351a33265337fa77ffeb82423f3ea21283cd9467bb03999266bc4"},
@@ -1357,6 +1432,8 @@ version = "2024.10.1"
 description = "The JSON Schema meta-schemas and vocabularies, exposed as a Registry"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "jsonschema_specifications-2024.10.1-py3-none-any.whl", hash = "sha256:a09a0680616357d9a0ecf05c12ad234479f549239d0f5b55f3deea67475da9bf"},
     {file = "jsonschema_specifications-2024.10.1.tar.gz", hash = "sha256:0f38b83639958ce1152d02a7f062902c41c8fd20d558b0c34344292d417ae272"},
@@ -1371,6 +1448,8 @@ version = "1.2.2"
 description = "a modern parsing library"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "lark-1.2.2-py3-none-any.whl", hash = "sha256:c2276486b02f0f1b90be155f2c8ba4a8e194d42775786db622faccd652d8e80c"},
     {file = "lark-1.2.2.tar.gz", hash = "sha256:ca807d0162cd16cef15a8feecb862d7319e7a09bdb13aef927968e45040fed80"},
@@ -1388,6 +1467,7 @@ version = "0.6.0"
 description = "Python logging made (stupidly) simple"
 optional = false
 python-versions = ">=3.5"
+groups = ["main"]
 files = [
     {file = "loguru-0.6.0-py3-none-any.whl", hash = "sha256:4e2414d534a2ab57573365b3e6d0234dfb1d84b68b7f3b948e6fb743860a77c3"},
     {file = "loguru-0.6.0.tar.gz", hash = "sha256:066bd06758d0a513e9836fd9c6b5a75bfb3fd36841f4b996bc60b547a309d41c"},
@@ -1398,7 +1478,7 @@ colorama = {version = ">=0.3.4", markers = "sys_platform == \"win32\""}
 win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""}
 
 [package.extras]
-dev = ["Sphinx (>=4.1.1)", "black (>=19.10b0)", "colorama (>=0.3.4)", "docutils (==0.16)", "flake8 (>=3.7.7)", "isort (>=5.1.1)", "pytest (>=4.6.2)", "pytest-cov (>=2.7.1)", "sphinx-autobuild (>=0.7.1)", "sphinx-rtd-theme (>=0.4.3)", "tox (>=3.9.0)"]
+dev = ["Sphinx (>=4.1.1) ; python_version >= \"3.6\"", "black (>=19.10b0) ; python_version >= \"3.6\"", "colorama (>=0.3.4)", "docutils (==0.16)", "flake8 (>=3.7.7)", "isort (>=5.1.1) ; python_version >= \"3.6\"", "pytest (>=4.6.2)", "pytest-cov (>=2.7.1)", "sphinx-autobuild (>=0.7.1) ; python_version >= \"3.6\"", "sphinx-rtd-theme (>=0.4.3) ; python_version >= \"3.6\"", "tox (>=3.9.0)"]
 
 [[package]]
 name = "markupsafe"
@@ -1406,6 +1486,8 @@ version = "3.0.2"
 description = "Safely add untrusted strings to HTML/XML markup."
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
 files = [
     {file = "MarkupSafe-3.0.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:7e94c425039cde14257288fd61dcfb01963e658efbc0ff54f5306b06054700f8"},
     {file = "MarkupSafe-3.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9e2d922824181480953426608b81967de705c3cef4d1af983af849d7bd619158"},
@@ -1476,6 +1558,8 @@ version = "0.4.1"
 description = ""
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "python_version >= \"3.13\" and extra == \"quantize\""
 files = [
     {file = "ml_dtypes-0.4.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:1fe8b5b5e70cd67211db94b05cfd58dace592f24489b038dc6f9fe347d2e07d5"},
     {file = "ml_dtypes-0.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c09a6d11d8475c2a9fd2bc0695628aec105f97cab3b3a3fb7c9660348ff7d24"},
@@ -1508,6 +1592,8 @@ version = "0.5.1"
 description = ""
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "python_version <= \"3.12\" and extra == \"quantize\""
 files = [
     {file = "ml_dtypes-0.5.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:bd73f51957949069573ff783563486339a9285d72e2f36c18e0c1aa9ca7eb190"},
     {file = "ml_dtypes-0.5.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:810512e2eccdfc3b41eefa3a27402371a3411453a1efc7e9c000318196140fed"},
@@ -1537,10 +1623,10 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.21", markers = "python_version < \"3.10\""},
-    {version = ">=1.21.2", markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.23.3", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\" and python_version < \"3.13\""},
+    {version = ">=1.21"},
+    {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
+    {version = ">=1.23.3", markers = "python_version >= \"3.11\""},
+    {version = ">=1.26.0", markers = "python_version == \"3.12\""},
 ]
 
 [package.extras]
@@ -1552,6 +1638,8 @@ version = "1.3.0"
 description = "Python library for arbitrary-precision floating-point arithmetic"
 optional = false
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
 files = [
     {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
     {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
@@ -1560,7 +1648,7 @@ files = [
 [package.extras]
 develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
 docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4)"]
+gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
 tests = ["pytest (>=4.6)"]
 
 [[package]]
@@ -1569,6 +1657,7 @@ version = "6.1.0"
 description = "multidict implementation"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "multidict-6.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3380252550e372e8511d49481bd836264c009adb826b23fefcc5dd3c69692f60"},
     {file = "multidict-6.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:99f826cbf970077383d7de805c0681799491cb939c25450b9b5b3ced03ca99f1"},
@@ -1673,6 +1762,8 @@ version = "0.70.15"
 description = "better multiprocessing and multithreading in Python"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "multiprocess-0.70.15-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:aa36c7ed16f508091438687fe9baa393a7a8e206731d321e443745e743a0d4e5"},
     {file = "multiprocess-0.70.15-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:20e024018c46d0d1602024c613007ac948f9754659e3853b0aa705e83f6931d8"},
@@ -1701,6 +1792,8 @@ version = "1.6.0"
 description = "Patch asyncio to allow nested event loops"
 optional = true
 python-versions = ">=3.5"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "nest_asyncio-1.6.0-py3-none-any.whl", hash = "sha256:87af6efd6b5e897c81050477ef65c62e2b2f35d51703cae01aff2905b1852e1c"},
     {file = "nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe"},
@@ -1712,6 +1805,8 @@ version = "3.2.1"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
 files = [
     {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"},
     {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"},
@@ -1730,6 +1825,7 @@ version = "1.26.4"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
     {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
@@ -1771,46 +1867,58 @@ files = [
 
 [[package]]
 name = "nvidia-cublas-cu12"
-version = "12.1.3.1"
+version = "12.4.5.8"
 description = "CUBLAS native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
-    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
+    {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0f8aa1706812e00b9f19dfe0cdb3999b092ccb8ca168c0db5b8ea712456fd9b3"},
+    {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b"},
+    {file = "nvidia_cublas_cu12-12.4.5.8-py3-none-win_amd64.whl", hash = "sha256:5a796786da89203a0657eda402bcdcec6180254a8ac22d72213abc42069522dc"},
 ]
 
 [[package]]
 name = "nvidia-cuda-cupti-cu12"
-version = "12.1.105"
+version = "12.4.127"
 description = "CUDA profiling tools runtime libs."
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
-    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
+    {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:79279b35cf6f91da114182a5ce1864997fd52294a87a16179ce275773799458a"},
+    {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb"},
+    {file = "nvidia_cuda_cupti_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:5688d203301ab051449a2b1cb6690fbe90d2b372f411521c86018b950f3d7922"},
 ]
 
 [[package]]
 name = "nvidia-cuda-nvrtc-cu12"
-version = "12.1.105"
+version = "12.4.127"
 description = "NVRTC native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
-    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0eedf14185e04b76aa05b1fea04133e59f465b6f960c0cbf4e37c3cb6b0ea198"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:a961b2f1d5f17b14867c619ceb99ef6fcec12e46612711bcec78eb05068a60ec"},
 ]
 
 [[package]]
 name = "nvidia-cuda-runtime-cu12"
-version = "12.1.105"
+version = "12.4.127"
 description = "CUDA Runtime native Libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
-    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
+    {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:961fe0e2e716a2a1d967aab7caee97512f71767f852f67432d572e36cb3a11f3"},
+    {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5"},
+    {file = "nvidia_cuda_runtime_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:09c2e35f48359752dfa822c09918211844a3d93c100a715d79b59591130c5e1e"},
 ]
 
 [[package]]
@@ -1819,6 +1927,8 @@ version = "9.1.0.70"
 description = "cuDNN runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
     {file = "nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f"},
     {file = "nvidia_cudnn_cu12-9.1.0.70-py3-none-win_amd64.whl", hash = "sha256:6278562929433d68365a07a4a1546c237ba2849852c0d4b2262a486e805b977a"},
@@ -1829,35 +1939,47 @@ nvidia-cublas-cu12 = "*"
 
 [[package]]
 name = "nvidia-cufft-cu12"
-version = "11.0.2.54"
+version = "11.2.1.3"
 description = "CUFFT native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
-    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
+    {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5dad8008fc7f92f5ddfa2101430917ce2ffacd86824914c82e28990ad7f00399"},
+    {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9"},
+    {file = "nvidia_cufft_cu12-11.2.1.3-py3-none-win_amd64.whl", hash = "sha256:d802f4954291101186078ccbe22fc285a902136f974d369540fd4a5333d1440b"},
 ]
 
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
 [[package]]
 name = "nvidia-curand-cu12"
-version = "10.3.2.106"
+version = "10.3.5.147"
 description = "CURAND native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
-    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
+    {file = "nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1f173f09e3e3c76ab084aba0de819c49e56614feae5c12f69883f4ae9bb5fad9"},
+    {file = "nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b"},
+    {file = "nvidia_curand_cu12-10.3.5.147-py3-none-win_amd64.whl", hash = "sha256:f307cc191f96efe9e8f05a87096abc20d08845a841889ef78cb06924437f6771"},
 ]
 
 [[package]]
 name = "nvidia-cusolver-cu12"
-version = "11.4.5.107"
+version = "11.6.1.9"
 description = "CUDA solver native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
-    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
+    {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d338f155f174f90724bbde3758b7ac375a70ce8e706d70b018dd3375545fc84e"},
+    {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260"},
+    {file = "nvidia_cusolver_cu12-11.6.1.9-py3-none-win_amd64.whl", hash = "sha256:e77314c9d7b694fcebc84f58989f3aa4fb4cb442f12ca1a9bde50f5e8f6d1b9c"},
 ]
 
 [package.dependencies]
@@ -1867,24 +1989,42 @@ nvidia-nvjitlink-cu12 = "*"
 
 [[package]]
 name = "nvidia-cusparse-cu12"
-version = "12.1.0.106"
+version = "12.3.1.170"
 description = "CUSPARSE native runtime libraries"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
-    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
+    {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_aarch64.whl", hash = "sha256:9d32f62896231ebe0480efd8a7f702e143c98cfaa0e8a76df3386c1ba2b54df3"},
+    {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1"},
+    {file = "nvidia_cusparse_cu12-12.3.1.170-py3-none-win_amd64.whl", hash = "sha256:9bc90fb087bc7b4c15641521f31c0371e9a612fc2ba12c338d3ae032e6b6797f"},
 ]
 
 [package.dependencies]
 nvidia-nvjitlink-cu12 = "*"
 
+[[package]]
+name = "nvidia-cusparselt-cu12"
+version = "0.6.2"
+description = "NVIDIA cuSPARSELt"
+optional = false
+python-versions = "*"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
+files = [
+    {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:067a7f6d03ea0d4841c85f0c6f1991c5dda98211f6302cb83a4ab234ee95bef8"},
+    {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:df2c24502fd76ebafe7457dbc4716b2fec071aabaed4fb7691a201cde03704d9"},
+    {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-win_amd64.whl", hash = "sha256:0057c91d230703924c0422feabe4ce768841f9b4b44d28586b6f6d2eb86fbe70"},
+]
+
 [[package]]
 name = "nvidia-ml-py"
 version = "12.570.86"
 description = "Python Bindings for the NVIDIA Management Library"
 optional = false
 python-versions = "*"
+groups = ["main"]
 files = [
     {file = "nvidia_ml_py-12.570.86-py3-none-any.whl", hash = "sha256:58907de35a845abd13dcb227f18298f3b5dd94a72d04c9e594e77711e95c0b51"},
     {file = "nvidia_ml_py-12.570.86.tar.gz", hash = "sha256:0508d4a0c7b6d015cf574530b95a62ed4fc89da3b8b47e1aefe6777db170ec8b"},
@@ -1892,36 +2032,42 @@ files = [
 
 [[package]]
 name = "nvidia-nccl-cu12"
-version = "2.20.5"
+version = "2.21.5"
 description = "NVIDIA Collective Communication Library (NCCL) Runtime"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"},
-    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"},
+    {file = "nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:8579076d30a8c24988834445f8d633c697d42397e92ffc3f63fa26766d25e0a0"},
 ]
 
 [[package]]
 name = "nvidia-nvjitlink-cu12"
-version = "12.8.61"
+version = "12.4.127"
 description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:45fd79f2ae20bd67e8bc411055939049873bfd8fac70ff13bd4865e0b9bdab17"},
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9b80ecab31085dda3ce3b41d043be0ec739216c3fc633b8abe212d5a30026df0"},
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-win_amd64.whl", hash = "sha256:1166a964d25fdc0eae497574d38824305195a5283324a21ccb0ce0c802cbf41c"},
+    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83"},
+    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57"},
+    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:fd9020c501d27d135f983c6d3e244b197a7ccad769e34df53a42e276b0e25fa1"},
 ]
 
 [[package]]
 name = "nvidia-nvtx-cu12"
-version = "12.1.105"
+version = "12.4.127"
 description = "NVIDIA Tools Extension"
 optional = false
 python-versions = ">=3"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\") and platform_system == \"Linux\" and platform_machine == \"x86_64\""
 files = [
-    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
-    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
+    {file = "nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7959ad635db13edf4fc65c06a6e9f9e55fc2f92596db928d169c0bb031e88ef3"},
+    {file = "nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a"},
+    {file = "nvidia_nvtx_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:641dccaaa1139f3ffb0d3164b4b84f9d253397e38246a4f2f36728b48566d485"},
 ]
 
 [[package]]
@@ -1930,6 +2076,7 @@ version = "1.21.0"
 description = "OpenTelemetry Python API"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_api-1.21.0-py3-none-any.whl", hash = "sha256:4bb86b28627b7e41098f0e93280fe4892a1abed1b79a19aec6f928f39b17dffb"},
     {file = "opentelemetry_api-1.21.0.tar.gz", hash = "sha256:d6185fd5043e000075d921822fd2d26b953eba8ca21b1e2fa360dd46a7686316"},
@@ -1945,6 +2092,7 @@ version = "1.21.0"
 description = "OpenTelemetry Collector Exporters"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_exporter_otlp-1.21.0-py3-none-any.whl", hash = "sha256:40552c016ad3f26c1650b0f08acbf0fef96d57b056a07d4dd00b6df3d5c27b7e"},
     {file = "opentelemetry_exporter_otlp-1.21.0.tar.gz", hash = "sha256:2a959e6893b14d737f259d309e972f6b7343ab2be58e592fa6d8c23127f62875"},
@@ -1960,6 +2108,7 @@ version = "1.21.0"
 description = "OpenTelemetry Protobuf encoding"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_exporter_otlp_proto_common-1.21.0-py3-none-any.whl", hash = "sha256:97b1022b38270ec65d11fbfa348e0cd49d12006485c2321ea3b1b7037d42b6ec"},
     {file = "opentelemetry_exporter_otlp_proto_common-1.21.0.tar.gz", hash = "sha256:61db274d8a68d636fb2ec2a0f281922949361cdd8236e25ff5539edf942b3226"},
@@ -1975,6 +2124,7 @@ version = "1.21.0"
 description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_exporter_otlp_proto_grpc-1.21.0-py3-none-any.whl", hash = "sha256:ab37c63d6cb58d6506f76d71d07018eb1f561d83e642a8f5aa53dddf306087a4"},
     {file = "opentelemetry_exporter_otlp_proto_grpc-1.21.0.tar.gz", hash = "sha256:a497c5611245a2d17d9aa1e1cbb7ab567843d53231dcc844a62cea9f0924ffa7"},
@@ -1999,6 +2149,7 @@ version = "1.21.0"
 description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_exporter_otlp_proto_http-1.21.0-py3-none-any.whl", hash = "sha256:56837773de6fb2714c01fc4895caebe876f6397bbc4d16afddf89e1299a55ee2"},
     {file = "opentelemetry_exporter_otlp_proto_http-1.21.0.tar.gz", hash = "sha256:19d60afa4ae8597f7ef61ad75c8b6c6b7ef8cb73a33fb4aed4dbc86d5c8d3301"},
@@ -2023,6 +2174,7 @@ version = "0.42b0"
 description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_instrumentation-0.42b0-py3-none-any.whl", hash = "sha256:65ae54ddb90ca2d05d2d16bf6863173e7141eba1bbbf41fc9bbb02446adbe369"},
     {file = "opentelemetry_instrumentation-0.42b0.tar.gz", hash = "sha256:6a653a1fed0f76eea32885321d77c750483e987eeefa4cbf219fc83559543198"},
@@ -2039,6 +2191,7 @@ version = "0.42b0"
 description = "OpenTelemetry gRPC instrumentation"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_instrumentation_grpc-0.42b0-py3-none-any.whl", hash = "sha256:30ce476de63b4d09e402ed3225d8308e124b6c9764bb202f05c16b7f7cb62f9d"},
     {file = "opentelemetry_instrumentation_grpc-0.42b0.tar.gz", hash = "sha256:4c5701b1e54765f9000336a243ddfd4ecf3f76cd62070a8e7f3054a3b928679e"},
@@ -2061,6 +2214,7 @@ version = "1.21.0"
 description = "OpenTelemetry Python Proto"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_proto-1.21.0-py3-none-any.whl", hash = "sha256:32fc4248e83eebd80994e13963e683f25f3b443226336bb12b5b6d53638f50ba"},
     {file = "opentelemetry_proto-1.21.0.tar.gz", hash = "sha256:7d5172c29ed1b525b5ecf4ebe758c7138a9224441b3cfe683d0a237c33b1941f"},
@@ -2075,6 +2229,7 @@ version = "1.21.0"
 description = "OpenTelemetry Python SDK"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_sdk-1.21.0-py3-none-any.whl", hash = "sha256:9fe633243a8c655fedace3a0b89ccdfc654c0290ea2d8e839bd5db3131186f73"},
     {file = "opentelemetry_sdk-1.21.0.tar.gz", hash = "sha256:3ec8cd3020328d6bc5c9991ccaf9ae820ccb6395a5648d9a95d3ec88275b8879"},
@@ -2091,6 +2246,7 @@ version = "0.42b0"
 description = "OpenTelemetry Semantic Conventions"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "opentelemetry_semantic_conventions-0.42b0-py3-none-any.whl", hash = "sha256:5cd719cbfec448af658860796c5d0fcea2fdf0945a2bed2363f42cb1ee39f526"},
     {file = "opentelemetry_semantic_conventions-0.42b0.tar.gz", hash = "sha256:44ae67a0a3252a05072877857e5cc1242c98d4cf12870159f1a94bec800d38ec"},
@@ -2102,6 +2258,8 @@ version = "0.1.14"
 description = "Probabilistic Generative Model Programming"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "outlines-0.1.14-py3-none-any.whl", hash = "sha256:a5090d50c368ed078051de25686a53032cd9f1702528afc646c3dae9482598ce"},
     {file = "outlines-0.1.14.tar.gz", hash = "sha256:35f0c49fc7eedc64ec08e2d6fd434845cf63cc0c3fdeb5900ac7902d074e57be"},
@@ -2133,7 +2291,7 @@ llamacpp = ["datasets", "llama-cpp-python", "numpy (<2)", "transformers"]
 mlxlm = ["datasets", "mlx-lm"]
 openai = ["openai"]
 serve = ["fastapi", "pydantic (>=2.0)", "uvicorn", "vllm (>=0.3.0)"]
-test = ["accelerate", "beartype (<0.16.0)", "coverage[toml] (>=5.1)", "datasets", "diff-cover", "exllamav2", "huggingface_hub", "jax", "llama-cpp-python", "mlx-lm (>=0.19.2)", "openai (>=1.0.0)", "pillow", "pre-commit", "pytest", "pytest-benchmark", "pytest-cov", "pytest-mock", "responses", "transformers", "vllm"]
+test = ["accelerate", "beartype (<0.16.0)", "coverage[toml] (>=5.1)", "datasets", "diff-cover", "exllamav2", "huggingface_hub", "jax", "llama-cpp-python", "mlx-lm (>=0.19.2) ; platform_machine == \"arm64\" and sys_platform == \"darwin\"", "openai (>=1.0.0)", "pillow", "pre-commit", "pytest", "pytest-benchmark", "pytest-cov", "pytest-mock", "responses", "transformers", "vllm ; sys_platform == \"linux\""]
 transformers = ["accelerate", "datasets", "numpy (<2)", "transformers"]
 vllm = ["numpy (<2)", "transformers", "vllm"]
 
@@ -2143,6 +2301,8 @@ version = "0.1.26"
 description = "Structured Text Generation in Rust"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "outlines_core-0.1.26-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:6a962a7452e7ac170fa04d405342cadae2d28fafa5b1830cef7aa610257ed32f"},
     {file = "outlines_core-0.1.26-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:15a3684fa29564da2db03934cf0097bef3e871f70d3af0ef2b52fdb886da2e09"},
@@ -2184,6 +2344,7 @@ version = "24.2"
 description = "Core utilities for Python packages"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev"]
 files = [
     {file = "packaging-24.2-py3-none-any.whl", hash = "sha256:09abb1bccd265c01f4a3aa3f7a7db064b36514d2cba19a2f694fe6150451a759"},
     {file = "packaging-24.2.tar.gz", hash = "sha256:c228a6dc5e932d346bc5739379109d49e8853dd8223571c7c5b55260edc0b97f"},
@@ -2195,6 +2356,8 @@ version = "2.2.3"
 description = "Powerful data structures for data analysis, time series, and statistics"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5"},
     {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"},
@@ -2281,6 +2444,8 @@ version = "0.4.0"
 description = "Parameter-Efficient Fine-Tuning (PEFT)"
 optional = true
 python-versions = ">=3.8.0"
+groups = ["main"]
+markers = "extra == \"peft\""
 files = [
     {file = "peft-0.4.0-py3-none-any.whl", hash = "sha256:2cf992772a6d703814477e0bdcdadd68cb8ea388111ce2d793dd2ff0e438f357"},
     {file = "peft-0.4.0.tar.gz", hash = "sha256:e768fa22d6e9f32aa7e891f0d06f355960278ca4dc0cdd96bff71f6f06269207"},
@@ -2308,6 +2473,7 @@ version = "10.4.0"
 description = "Python Imaging Library (Fork)"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "pillow-10.4.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:4d9667937cfa347525b319ae34375c37b9ee6b525440f3ef48542fcf66f2731e"},
     {file = "pillow-10.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:543f3dc61c18dafb755773efc89aae60d06b6596a63914107f75459cf984164d"},
@@ -2396,7 +2562,7 @@ docs = ["furo", "olefile", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-inline
 fpx = ["olefile"]
 mic = ["olefile"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
-typing = ["typing-extensions"]
+typing = ["typing-extensions ; python_version < \"3.10\""]
 xmp = ["defusedxml"]
 
 [[package]]
@@ -2405,6 +2571,7 @@ version = "1.5.0"
 description = "plugin and hook calling mechanisms for python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev"]
 files = [
     {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
     {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
@@ -2420,6 +2587,7 @@ version = "0.20.0"
 description = "Python client for the Prometheus monitoring system."
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "prometheus_client-0.20.0-py3-none-any.whl", hash = "sha256:cde524a85bce83ca359cc837f28b8c0db5cac7aa653a588fd7e84ba061c329e7"},
     {file = "prometheus_client-0.20.0.tar.gz", hash = "sha256:287629d00b147a32dcb2be0b9df905da599b2d82f80377083ec8463309a4bb89"},
@@ -2434,6 +2602,7 @@ version = "0.3.0"
 description = "Accelerated property cache"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "propcache-0.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:efa44f64c37cc30c9f05932c740a8b40ce359f51882c70883cc95feac842da4d"},
     {file = "propcache-0.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2383a17385d9800b6eb5855c2f05ee550f803878f344f58b6e194de08b96352c"},
@@ -2541,6 +2710,7 @@ version = "4.25.6"
 description = ""
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev"]
 files = [
     {file = "protobuf-4.25.6-cp310-abi3-win32.whl", hash = "sha256:61df6b5786e2b49fc0055f636c1e8f0aff263808bb724b95b164685ac1bcc13a"},
     {file = "protobuf-4.25.6-cp310-abi3-win_amd64.whl", hash = "sha256:b8f837bfb77513fe0e2f263250f423217a173b6d85135be4d81e96a4653bcd3c"},
@@ -2561,6 +2731,8 @@ version = "7.0.0"
 description = "Cross-platform lib for process and system monitoring in Python.  NOTE: the syntax of this script MUST be kept compatible with Python 2.7."
 optional = true
 python-versions = ">=3.6"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\""
 files = [
     {file = "psutil-7.0.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:101d71dc322e3cffd7cea0650b09b3d08b8e7c4109dd6809fe452dfd00e58b25"},
     {file = "psutil-7.0.0-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:39db632f6bb862eeccf56660871433e111b6ea58f2caea825571951d4b6aa3da"},
@@ -2584,6 +2756,7 @@ version = "9.0.0"
 description = "Get CPU info with pure Python"
 optional = false
 python-versions = "*"
+groups = ["main"]
 files = [
     {file = "py-cpuinfo-9.0.0.tar.gz", hash = "sha256:3cdbbf3fac90dc6f118bfd64384f309edeadd902d7c8fb17f02ffa1fc3f49690"},
     {file = "py_cpuinfo-9.0.0-py3-none-any.whl", hash = "sha256:859625bc251f64e21f077d099d4162689c762b5d6a4c3c97553d56241c9674d5"},
@@ -2595,6 +2768,8 @@ version = "19.0.1"
 description = "Python library for Apache Arrow"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "pyarrow-19.0.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:fc28912a2dc924dddc2087679cc8b7263accc71b9ff025a1362b004711661a69"},
     {file = "pyarrow-19.0.1-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:fca15aabbe9b8355800d923cc2e82c8ef514af321e18b437c3d782aa884eaeec"},
@@ -2649,6 +2824,8 @@ version = "24.6.1"
 description = "ISO country, subdivision, language, currency and script definitions and their translations"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "pycountry-24.6.1-py3-none-any.whl", hash = "sha256:f1a4fb391cd7214f8eefd39556d740adcc233c778a27f8942c8dca351d6ce06f"},
     {file = "pycountry-24.6.1.tar.gz", hash = "sha256:b61b3faccea67f87d10c1f2b0fc0be714409e8fcdcc1315613174f6466c10221"},
@@ -2660,6 +2837,8 @@ version = "2.22"
 description = "C parser in Python"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "pycparser-2.22-py3-none-any.whl", hash = "sha256:c3702b6d3dd8c7abc1afa565d7e63d53a1d0bd86cdc24edd75470f4de499cfcc"},
     {file = "pycparser-2.22.tar.gz", hash = "sha256:491c8be9c040f5390f5bf44a5b07752bd07f56edf992381b05c701439eec10f6"},
@@ -2671,6 +2850,8 @@ version = "2.10.6"
 description = "Data validation using Python type hints"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "pydantic-2.10.6-py3-none-any.whl", hash = "sha256:427d664bf0b8a2b34ff5dd0f5a18df00591adcee7198fbd71981054cef37b584"},
     {file = "pydantic-2.10.6.tar.gz", hash = "sha256:ca5daa827cce33de7a42be142548b0096bf05a7e7b365aebfa5f8eeec7128236"},
@@ -2683,7 +2864,7 @@ typing-extensions = ">=4.12.2"
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
-timezone = ["tzdata"]
+timezone = ["tzdata ; python_version >= \"3.9\" and platform_system == \"Windows\""]
 
 [[package]]
 name = "pydantic-core"
@@ -2691,6 +2872,8 @@ version = "2.27.2"
 description = "Core functionality for Pydantic validation and serialization"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "pydantic_core-2.27.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2d367ca20b2f14095a8f4fa1210f5a7b78b8a20009ecced6b12818f455b1e9fa"},
     {file = "pydantic_core-2.27.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:491a2b73db93fab69731eaee494f320faa4e093dbed776be1a829c2eb222c34c"},
@@ -2803,6 +2986,7 @@ version = "7.4.4"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev"]
 files = [
     {file = "pytest-7.4.4-py3-none-any.whl", hash = "sha256:b090cdf5ed60bf4c45261be03239c2c1c22df034fbffe691abe93cd80cea01d8"},
     {file = "pytest-7.4.4.tar.gz", hash = "sha256:2cf0005922c6ace4a3e2ec8b4080eb0d9753fdc93107415332f50ce9e7994280"},
@@ -2825,6 +3009,8 @@ version = "3.6.1"
 description = "pytest xdist plugin for distributed testing, most importantly across multiple CPUs"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "pytest_xdist-3.6.1-py3-none-any.whl", hash = "sha256:9ed4adfb68a016610848639bb7e02c9352d5d9f03d04809919e2dafc3be4cca7"},
     {file = "pytest_xdist-3.6.1.tar.gz", hash = "sha256:ead156a4db231eec769737f57668ef58a2084a34b2e55c4a8fa20d861107300d"},
@@ -2845,6 +3031,7 @@ version = "2.9.0.post0"
 description = "Extensions to the standard Python datetime module"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+groups = ["main"]
 files = [
     {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"},
     {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"},
@@ -2859,6 +3046,8 @@ version = "2025.1"
 description = "World timezone definitions, modern and historical"
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "pytz-2025.1-py2.py3-none-any.whl", hash = "sha256:89dd22dca55b46eac6eda23b2d72721bf1bdfef212645d81513ef5d03038de57"},
     {file = "pytz-2025.1.tar.gz", hash = "sha256:c2db42be2a2518b28e65f9207c4d05e6ff547d1efa4086469ef855e4ab70178e"},
@@ -2870,6 +3059,7 @@ version = "6.0.2"
 description = "YAML parser and emitter for Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "PyYAML-6.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0a9a2848a5b7feac301353437eb7d5957887edbf81d56e903999a75a3d743086"},
     {file = "PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29717114e51c84ddfba879543fb232a6ed60086602313ca38cce623c1d62cfbf"},
@@ -2932,6 +3122,8 @@ version = "3.12.2"
 description = "rapid fuzzy string matching"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "rapidfuzz-3.12.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0b9a75e0385a861178adf59e86d6616cbd0d5adca7228dc9eeabf6f62cf5b0b1"},
     {file = "rapidfuzz-3.12.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6906a7eb458731e3dd2495af1d0410e23a21a2a2b7ced535e6d5cd15cb69afc5"},
@@ -3038,6 +3230,8 @@ version = "0.36.2"
 description = "JSON Referencing + Python"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "referencing-0.36.2-py3-none-any.whl", hash = "sha256:e8699adbbf8b5c7de96d8ffa0eb5c158b3beafce084968e2ea8bb08c6794dcd0"},
     {file = "referencing-0.36.2.tar.gz", hash = "sha256:df2e89862cd09deabbdba16944cc3f10feb6b3e6f18e902f7cc25609a34775aa"},
@@ -3054,6 +3248,7 @@ version = "2024.11.6"
 description = "Alternative regular expression module, to replace re."
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "regex-2024.11.6-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff590880083d60acc0433f9c3f713c51f7ac6ebb9adf889c79a261ecf541aa91"},
     {file = "regex-2024.11.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:658f90550f38270639e83ce492f27d2c8d2cd63805c65a13a14d36ca126753f0"},
@@ -3157,6 +3352,7 @@ version = "2.32.3"
 description = "Python HTTP for Humans."
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
     {file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
@@ -3178,6 +3374,8 @@ version = "0.23.1"
 description = "Python bindings to Rust's persistent data structures (rpds)"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"outlines\""
 files = [
     {file = "rpds_py-0.23.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2a54027554ce9b129fc3d633c92fa33b30de9f08bc61b32c053dc9b537266fed"},
     {file = "rpds_py-0.23.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b5ef909a37e9738d146519657a1aab4584018746a18f71c692f2f22168ece40c"},
@@ -3290,6 +3488,7 @@ version = "0.11.4"
 description = "An Amazon S3 Transfer Manager"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "s3transfer-0.11.4-py3-none-any.whl", hash = "sha256:ac265fa68318763a03bf2dc4f39d5cbd6a9e178d81cc9483ad27da33637e320d"},
     {file = "s3transfer-0.11.4.tar.gz", hash = "sha256:559f161658e1cf0a911f45940552c696735f5c74e64362e515f333ebed87d679"},
@@ -3307,6 +3506,7 @@ version = "0.4.2"
 description = ""
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "safetensors-0.4.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:69d8bb8384dc2cb5b72c36c4d6980771b293d1a1377b378763f5e37b6bb8d133"},
     {file = "safetensors-0.4.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3d420e19fcef96d0067f4de4699682b4bbd85fc8fea0bd45fcd961fdf3e8c82c"},
@@ -3439,6 +3639,7 @@ version = "1.13.1"
 description = "Fundamental algorithms for scientific computing in Python"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "scipy-1.13.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:20335853b85e9a49ff7572ab453794298bcf0354d8068c5f6775a0eabf350aca"},
     {file = "scipy-1.13.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d605e9c23906d1994f55ace80e0125c587f96c020037ea6aa98d01b4bd2e222f"},
@@ -3481,6 +3682,7 @@ version = "0.2.0"
 description = "SentencePiece python wrapper"
 optional = false
 python-versions = "*"
+groups = ["main"]
 files = [
     {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:188779e1298a1c8b8253c7d3ad729cb0a9891e5cef5e5d07ce4592c54869e227"},
     {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bed9cf85b296fa2b76fc2547b9cbb691a523864cebaee86304c43a7b4cb1b452"},
@@ -3543,19 +3745,20 @@ version = "75.8.2"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.9"
+groups = ["main", "dev"]
 files = [
     {file = "setuptools-75.8.2-py3-none-any.whl", hash = "sha256:558e47c15f1811c1fa7adbd0096669bf76c1d3f433f58324df69f3f5ecac4e8f"},
     {file = "setuptools-75.8.2.tar.gz", hash = "sha256:4880473a969e5f23f2a2be3646b2dfd84af9028716d398e46192f84bc36900d2"},
 ]
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)", "ruff (>=0.8.0)"]
-core = ["importlib_metadata (>=6)", "jaraco.collections", "jaraco.functools (>=4)", "jaraco.text (>=3.7)", "more_itertools", "more_itertools (>=8.8)", "packaging", "packaging (>=24.2)", "platformdirs (>=4.2.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "ruff (>=0.8.0) ; sys_platform != \"cygwin\""]
+core = ["importlib_metadata (>=6) ; python_version < \"3.10\"", "jaraco.collections", "jaraco.functools (>=4)", "jaraco.text (>=3.7)", "more_itertools", "more_itertools (>=8.8)", "packaging", "packaging (>=24.2)", "platformdirs (>=4.2.2)", "tomli (>=2.0.1) ; python_version < \"3.11\"", "wheel (>=0.43.0)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.7.2)", "jaraco.test (>=5.5)", "packaging (>=24.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
-type = ["importlib_metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (==1.14.*)", "pytest-mypy"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.7.2)", "jaraco.test (>=5.5)", "packaging (>=24.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
+type = ["importlib_metadata (>=7.0.2) ; python_version < \"3.10\"", "jaraco.develop (>=7.21) ; sys_platform != \"cygwin\"", "mypy (==1.14.*)", "pytest-mypy"]
 
 [[package]]
 name = "six"
@@ -3563,6 +3766,7 @@ version = "1.17.0"
 description = "Python 2 and 3 compatibility utilities"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+groups = ["main"]
 files = [
     {file = "six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274"},
     {file = "six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81"},
@@ -3574,6 +3778,8 @@ version = "0.7.1"
 description = "Sparse Toolkit"
 optional = false
 python-versions = "*"
+groups = ["main"]
+markers = "sys_platform == \"linux\""
 files = [
     {file = "stanford_stk-0.7.1.tar.gz", hash = "sha256:fc46140c2572ee9c008b2ac67ee6656f63f49c1074da8aea0923fa8290702871"},
 ]
@@ -3588,13 +3794,15 @@ dev = ["absl-py"]
 
 [[package]]
 name = "sympy"
-version = "1.13.3"
+version = "1.13.1"
 description = "Computer algebra system (CAS) in Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
 files = [
-    {file = "sympy-1.13.3-py3-none-any.whl", hash = "sha256:54612cf55a62755ee71824ce692986f23c88ffa77207b30c1368eda4a7060f73"},
-    {file = "sympy-1.13.3.tar.gz", hash = "sha256:b27fd2c6530e0ab39e275fc9b683895367e51d5da91baa8d3d64db2565fec4d9"},
+    {file = "sympy-1.13.1-py3-none-any.whl", hash = "sha256:db36cdc64bf61b9b24578b6f7bab1ecdd2452cf008f34faa33776680c26d66f8"},
+    {file = "sympy-1.13.1.tar.gz", hash = "sha256:9cebf7e04ff162015ce31c9c6c9144daa34a93bd082f54fd8f12deca4f47515f"},
 ]
 
 [package.dependencies]
@@ -3609,6 +3817,8 @@ version = "0.9.0"
 description = "Pretty-print tabular data"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
     {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
@@ -3623,6 +3833,8 @@ version = "2.5.0"
 description = "ANSI color formatting for output in terminal"
 optional = true
 python-versions = ">=3.9"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "termcolor-2.5.0-py3-none-any.whl", hash = "sha256:37b17b5fc1e604945c2642c872a3764b5d547a48009871aea3edd3afa180afb8"},
     {file = "termcolor-2.5.0.tar.gz", hash = "sha256:998d8d27da6d48442e8e1f016119076b690d962507531df4890fcd2db2ef8a6f"},
@@ -3637,6 +3849,8 @@ version = "1.7.0"
 description = "module to create simple ASCII tables"
 optional = true
 python-versions = "*"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "texttable-1.7.0-py2.py3-none-any.whl", hash = "sha256:72227d592c82b3d7f672731ae73e4d1f88cd8e2ef5b075a7a7f01a23a3743917"},
     {file = "texttable-1.7.0.tar.gz", hash = "sha256:2d2068fb55115807d3ac77a4ca68fa48803e84ebb0ee2340f858107a36522638"},
@@ -3648,6 +3862,8 @@ version = "0.22.1"
 description = "Fuzzy string matching in python"
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "thefuzz-0.22.1-py3-none-any.whl", hash = "sha256:59729b33556850b90e1093c4cf9e618af6f2e4c985df193fdf3c5b5cf02ca481"},
     {file = "thefuzz-0.22.1.tar.gz", hash = "sha256:7138039a7ecf540da323792d8592ef9902b1d79eb78c147d4f20664de79f3680"},
@@ -3662,6 +3878,7 @@ version = "0.5.2"
 description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "tiktoken-0.5.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c4e654282ef05ec1bd06ead22141a9a1687991cef2c6a81bdd1284301abc71d"},
     {file = "tiktoken-0.5.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7b3134aa24319f42c27718c6967f3c1916a38a715a0fa73d33717ba121231307"},
@@ -3714,6 +3931,7 @@ version = "0.21.0"
 description = ""
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "tokenizers-0.21.0-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:3c4c93eae637e7d2aaae3d376f06085164e1660f89304c0ab2b1d08a406636b2"},
     {file = "tokenizers-0.21.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:f53ea537c925422a2e0e92a24cce96f6bc5046bbef24a1652a5edc8ba975f62e"},
@@ -3746,6 +3964,8 @@ version = "2.2.1"
 description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev"]
+markers = "python_version <= \"3.10\""
 files = [
     {file = "tomli-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678e4fa69e4575eb77d103de3df8a895e1591b48e740211bd1067378c69e8249"},
     {file = "tomli-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:023aa114dd824ade0100497eb2318602af309e5a55595f76b626d6d9f3b7b0a6"},
@@ -3783,31 +4003,33 @@ files = [
 
 [[package]]
 name = "torch"
-version = "2.4.0"
+version = "2.6.0"
 description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
 optional = false
-python-versions = ">=3.8.0"
-files = [
-    {file = "torch-2.4.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:4ed94583e244af51d6a8d28701ca5a9e02d1219e782f5a01dd401f90af17d8ac"},
-    {file = "torch-2.4.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:c4ca297b7bd58b506bfd6e78ffd14eb97c0e7797dcd7965df62f50bb575d8954"},
-    {file = "torch-2.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:2497cbc7b3c951d69b276ca51fe01c2865db67040ac67f5fc20b03e41d16ea4a"},
-    {file = "torch-2.4.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:685418ab93730efbee71528821ff54005596970dd497bf03c89204fb7e3f71de"},
-    {file = "torch-2.4.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:e743adadd8c8152bb8373543964551a7cb7cc20ba898dc8f9c0cdbe47c283de0"},
-    {file = "torch-2.4.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:7334325c0292cbd5c2eac085f449bf57d3690932eac37027e193ba775703c9e6"},
-    {file = "torch-2.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:97730014da4c57ffacb3c09298c6ce05400606e890bd7a05008d13dd086e46b1"},
-    {file = "torch-2.4.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:f169b4ea6dc93b3a33319611fcc47dc1406e4dd539844dcbd2dec4c1b96e166d"},
-    {file = "torch-2.4.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:997084a0f9784d2a89095a6dc67c7925e21bf25dea0b3d069b41195016ccfcbb"},
-    {file = "torch-2.4.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:bc3988e8b36d1e8b998d143255d9408d8c75da4ab6dd0dcfd23b623dfb0f0f57"},
-    {file = "torch-2.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:3374128bbf7e62cdaed6c237bfd39809fbcfaa576bee91e904706840c3f2195c"},
-    {file = "torch-2.4.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:91aaf00bfe1ffa44dc5b52809d9a95129fca10212eca3ac26420eb11727c6288"},
-    {file = "torch-2.4.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:cc30457ea5489c62747d3306438af00c606b509d78822a88f804202ba63111ed"},
-    {file = "torch-2.4.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:a046491aaf96d1215e65e1fa85911ef2ded6d49ea34c8df4d0638879f2402eef"},
-    {file = "torch-2.4.0-cp38-cp38-win_amd64.whl", hash = "sha256:688eec9240f3ce775f22e1e1a5ab9894f3d5fe60f3f586deb7dbd23a46a83916"},
-    {file = "torch-2.4.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:3af4de2a618fb065e78404c4ba27a818a7b7957eaeff28c6c66ce7fb504b68b8"},
-    {file = "torch-2.4.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:618808d3f610d5f180e47a697d4ec90b810953bb1e020f424b2ac7fb0884b545"},
-    {file = "torch-2.4.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:ed765d232d23566052ba83632ec73a4fccde00b4c94ad45d63b471b09d63b7a7"},
-    {file = "torch-2.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:a2feb98ac470109472fb10dfef38622a7ee08482a16c357863ebc7bc7db7c8f7"},
-    {file = "torch-2.4.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:8940fc8b97a4c61fdb5d46a368f21f4a3a562a17879e932eb51a5ec62310cb31"},
+python-versions = ">=3.9.0"
+groups = ["main"]
+markers = "extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\" or sys_platform == \"linux\""
+files = [
+    {file = "torch-2.6.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:6860df13d9911ac158f4c44031609700e1eba07916fff62e21e6ffa0a9e01961"},
+    {file = "torch-2.6.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:c4f103a49830ce4c7561ef4434cc7926e5a5fe4e5eb100c19ab36ea1e2b634ab"},
+    {file = "torch-2.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:56eeaf2ecac90da5d9e35f7f35eb286da82673ec3c582e310a8d1631a1c02341"},
+    {file = "torch-2.6.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:09e06f9949e1a0518c5b09fe95295bc9661f219d9ecb6f9893e5123e10696628"},
+    {file = "torch-2.6.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:7979834102cd5b7a43cc64e87f2f3b14bd0e1458f06e9f88ffa386d07c7446e1"},
+    {file = "torch-2.6.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ccbd0320411fe1a3b3fec7b4d3185aa7d0c52adac94480ab024b5c8f74a0bf1d"},
+    {file = "torch-2.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:46763dcb051180ce1ed23d1891d9b1598e07d051ce4c9d14307029809c4d64f7"},
+    {file = "torch-2.6.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:94fc63b3b4bedd327af588696559f68c264440e2503cc9e6954019473d74ae21"},
+    {file = "torch-2.6.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:2bb8987f3bb1ef2675897034402373ddfc8f5ef0e156e2d8cfc47cacafdda4a9"},
+    {file = "torch-2.6.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:b789069020c5588c70d5c2158ac0aa23fd24a028f34a8b4fcb8fcb4d7efcf5fb"},
+    {file = "torch-2.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:7e1448426d0ba3620408218b50aa6ada88aeae34f7a239ba5431f6c8774b1239"},
+    {file = "torch-2.6.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:9a610afe216a85a8b9bc9f8365ed561535c93e804c2a317ef7fabcc5deda0989"},
+    {file = "torch-2.6.0-cp313-cp313-manylinux1_x86_64.whl", hash = "sha256:4874a73507a300a5d089ceaff616a569e7bb7c613c56f37f63ec3ffac65259cf"},
+    {file = "torch-2.6.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a0d5e1b9874c1a6c25556840ab8920569a7a4137afa8a63a32cee0bc7d89bd4b"},
+    {file = "torch-2.6.0-cp313-cp313-win_amd64.whl", hash = "sha256:510c73251bee9ba02ae1cb6c9d4ee0907b3ce6020e62784e2d7598e0cfa4d6cc"},
+    {file = "torch-2.6.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:ff96f4038f8af9f7ec4231710ed4549da1bdebad95923953a25045dcf6fd87e2"},
+    {file = "torch-2.6.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9ea955317cfcd3852b1402b62af258ce735c2edeee42ca9419b6bc889e5ae053"},
+    {file = "torch-2.6.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bb2c6c3e65049f081940f5ab15c9136c7de40d3f01192541c920a07c7c585b7e"},
+    {file = "torch-2.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:683410f97984103148e31b38a8631acf31c3034c020c0f4d26171e7626d8317a"},
+    {file = "torch-2.6.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:265f70de5fd45b864d924b64be1797f86e76c8e48a02c2a3a6fc7ec247d2226c"},
 ]
 
 [package.dependencies]
@@ -3815,24 +4037,27 @@ filelock = "*"
 fsspec = "*"
 jinja2 = "*"
 networkx = "*"
-nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cublas-cu12 = {version = "12.4.5.8", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
 nvidia-cudnn-cu12 = {version = "9.1.0.70", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-sympy = "*"
-triton = {version = "3.0.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.13\""}
-typing-extensions = ">=4.8.0"
+nvidia-cufft-cu12 = {version = "11.2.1.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.5.147", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.6.1.9", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.3.1.170", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparselt-cu12 = {version = "0.6.2", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.21.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvjitlink-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+setuptools = {version = "*", markers = "python_version >= \"3.12\""}
+sympy = {version = "1.13.1", markers = "python_version >= \"3.9\""}
+triton = {version = "3.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+typing-extensions = ">=4.10.0"
 
 [package.extras]
 opt-einsum = ["opt-einsum (>=3.3)"]
-optree = ["optree (>=0.11.0)"]
+optree = ["optree (>=0.13.0)"]
 
 [[package]]
 name = "tornado"
@@ -3840,6 +4065,8 @@ version = "6.4.2"
 description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
 optional = true
 python-versions = ">=3.8"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "tornado-6.4.2-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e828cce1123e9e44ae2a50a9de3055497ab1d0aeb440c5ac23064d9e44880da1"},
     {file = "tornado-6.4.2-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:072ce12ada169c5b00b7d92a99ba089447ccc993ea2143c9ede887e0937aa803"},
@@ -3860,6 +4087,7 @@ version = "4.67.1"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2"},
     {file = "tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2"},
@@ -3881,6 +4109,7 @@ version = "4.49.0"
 description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
 optional = false
 python-versions = ">=3.9.0"
+groups = ["main"]
 files = [
     {file = "transformers-4.49.0-py3-none-any.whl", hash = "sha256:6b4fded1c5fee04d384b1014495b4235a2b53c87503d7d592423c06128cbbe03"},
     {file = "transformers-4.49.0.tar.gz", hash = "sha256:7e40e640b5b8dc3f48743f5f5adbdce3660c82baafbd3afdfc04143cdbd2089e"},
@@ -3946,21 +4175,20 @@ vision = ["Pillow (>=10.0.1,<=15.0)"]
 
 [[package]]
 name = "triton"
-version = "3.0.0"
+version = "3.2.0"
 description = "A language and compiler for custom Deep Learning operations"
 optional = false
 python-versions = "*"
+groups = ["main"]
+markers = "(extra == \"accelerate\" or extra == \"quantize\" or extra == \"peft\" or extra == \"bnb\" or extra == \"outlines\" or extra == \"torch\") and platform_system == \"Linux\" and platform_machine == \"x86_64\" or sys_platform == \"linux\""
 files = [
-    {file = "triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a"},
-    {file = "triton-3.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5ce8520437c602fb633f1324cc3871c47bee3b67acf9756c1a66309b60e3216c"},
-    {file = "triton-3.0.0-1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:34e509deb77f1c067d8640725ef00c5cbfcb2052a1a3cb6a6d343841f92624eb"},
-    {file = "triton-3.0.0-1-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:bcbf3b1c48af6a28011a5c40a5b3b9b5330530c3827716b5fbf6d7adcc1e53e9"},
-    {file = "triton-3.0.0-1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6e5727202f7078c56f91ff13ad0c1abab14a0e7f2c87e91b12b6f64f3e8ae609"},
+    {file = "triton-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3e54983cd51875855da7c68ec05c05cf8bb08df361b1d5b69e05e40b0c9bd62"},
+    {file = "triton-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220"},
+    {file = "triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d9b215efc1c26fa7eefb9a157915c92d52e000d2bf83e5f69704047e63f125c"},
+    {file = "triton-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5dfa23ba84541d7c0a531dfce76d8bcd19159d50a4a8b14ad01e91734a5c1b0"},
+    {file = "triton-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee"},
 ]
 
-[package.dependencies]
-filelock = "*"
-
 [package.extras]
 build = ["cmake (>=3.20)", "lit"]
 tests = ["autopep8", "flake8", "isort", "llnl-hatchet", "numpy", "pytest", "scipy (>=1.7.1)"]
@@ -3972,6 +4200,7 @@ version = "0.6.1"
 description = "Typer, build great CLIs. Easy to code. Based on Python type hints."
 optional = false
 python-versions = ">=3.6"
+groups = ["main"]
 files = [
     {file = "typer-0.6.1-py3-none-any.whl", hash = "sha256:54b19e5df18654070a82f8c2aa1da456a4ac16a2a83e6dcd9f170e291c56338e"},
     {file = "typer-0.6.1.tar.gz", hash = "sha256:2d5720a5e63f73eaf31edaa15f6ab87f35f0690f8ca233017d7d23d743a91d73"},
@@ -3992,6 +4221,7 @@ version = "4.12.2"
 description = "Backported and Experimental Type Hints for Python 3.8+"
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"},
     {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
@@ -4003,6 +4233,8 @@ version = "2025.1"
 description = "Provider of IANA time zone data"
 optional = true
 python-versions = ">=2"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "tzdata-2025.1-py2.py3-none-any.whl", hash = "sha256:7e127113816800496f027041c570f50bcd464a020098a3b6b199517772303639"},
     {file = "tzdata-2025.1.tar.gz", hash = "sha256:24894909e88cdb28bd1636c6887801df64cb485bd593f2fd83ef29075a81d694"},
@@ -4014,14 +4246,15 @@ version = "1.26.19"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+groups = ["main"]
 files = [
     {file = "urllib3-1.26.19-py2.py3-none-any.whl", hash = "sha256:37a0344459b199fce0e80b0d3569837ec6b6937435c5244e7fd73fa6006830f3"},
     {file = "urllib3-1.26.19.tar.gz", hash = "sha256:3e3d753a8618b86d7de333b4223005f68720bcd6a7d2bcb9fbd2229ec7c1e429"},
 ]
 
 [package.extras]
-brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
-secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
 [[package]]
@@ -4030,13 +4263,15 @@ version = "1.2.0"
 description = "A small Python utility to set file creation time on Windows"
 optional = false
 python-versions = ">=3.5"
+groups = ["main"]
+markers = "sys_platform == \"win32\""
 files = [
     {file = "win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390"},
     {file = "win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0"},
 ]
 
 [package.extras]
-dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
+dev = ["black (>=19.3b0) ; python_version >= \"3.6\"", "pytest (>=4.6.2)"]
 
 [[package]]
 name = "wrapt"
@@ -4044,6 +4279,7 @@ version = "1.17.2"
 description = "Module for decorators, wrappers and monkey patching."
 optional = false
 python-versions = ">=3.8"
+groups = ["main"]
 files = [
     {file = "wrapt-1.17.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3d57c572081fed831ad2d26fd430d565b76aa277ed1d30ff4d40670b1c0dd984"},
     {file = "wrapt-1.17.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b5e251054542ae57ac7f3fba5d10bfff615b6c2fb09abeb37d2f1463f841ae22"},
@@ -4132,6 +4368,8 @@ version = "3.5.0"
 description = "Python binding for xxHash"
 optional = true
 python-versions = ">=3.7"
+groups = ["main"]
+markers = "extra == \"quantize\""
 files = [
     {file = "xxhash-3.5.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ece616532c499ee9afbb83078b1b952beffef121d989841f7f4b3dc5ac0fd212"},
     {file = "xxhash-3.5.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3171f693dbc2cef6477054a665dc255d996646b4023fe56cb4db80e26f4cc520"},
@@ -4264,6 +4502,7 @@ version = "1.18.3"
 description = "Yet another URL library"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "yarl-1.18.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:7df647e8edd71f000a5208fe6ff8c382a1de8edfbccdbbfe649d263de07d8c34"},
     {file = "yarl-1.18.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c69697d3adff5aa4f874b19c0e4ed65180ceed6318ec856ebc423aa5850d84f7"},
@@ -4360,17 +4599,18 @@ version = "3.21.0"
 description = "Backport of pathlib-compatible object wrapper for zip files"
 optional = false
 python-versions = ">=3.9"
+groups = ["main"]
 files = [
     {file = "zipp-3.21.0-py3-none-any.whl", hash = "sha256:ac1bbe05fd2991f160ebce24ffbac5f6d11d83dc90891255885223d42b3cd931"},
     {file = "zipp-3.21.0.tar.gz", hash = "sha256:2c9958f6430a2040341a52eb608ed6dd93ef4392e02ffe219417c1b28b5dd1f4"},
 ]
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
+test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
 [extras]
@@ -4382,6 +4622,6 @@ quantize = ["accelerate", "datasets", "hqq", "texttable"]
 torch = ["torch"]
 
 [metadata]
-lock-version = "2.0"
+lock-version = "2.1"
 python-versions = "^3.9"
-content-hash = "2fe6516d7d84aac9f84b12650ff7e8ed3c9fbd87326fb7afb04f16d3e3b1d919"
+content-hash = "f2f9e9e58b1efcc137628f997509becf83fb44a3056b8ad2deaf3ff22a795fb6"
diff --git a/server/pyproject.toml b/server/pyproject.toml
index 2f46784bd..07e6e1200 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -36,7 +36,7 @@ einops = "^0.6.1"
 tiktoken = "^0.5.2"
 texttable = { version = "^1.6.7", optional = true }
 datasets = { version = "^2.14.0", optional = true }
-torch = { version = "2.4.0", optional = true }
+torch = { version = "2.6.0", optional = true }
 peft = { version = "0.4.0", optional = true }
 boto3 = "^1.28.34"
 urllib3 = "1.26.19"