Skip to content
Merged
Show file tree
Hide file tree
Changes from 7 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions tests/v1/entrypoints/llm/test_struct_output_generate.py
Original file line number Diff line number Diff line change
Expand Up @@ -677,9 +677,14 @@ def test_structured_output_with_reasoning_matrices(
reasoning, content = run_reasoning_extraction(reasoner, [generated_text])
print(f"Prompt: {prompt!r}\nReasoning: {reasoning!r}\nContent: {content!r}")

assert content is not None and reasoning is not None
output_json = json.loads(content)
jsonschema.validate(instance=output_json, schema=reasoning_schema)
if "Qwen3" in model_name:
assert content is not None

assert reasoning is not None

if content is not None:
output_json = json.loads(content)
jsonschema.validate(instance=output_json, schema=reasoning_schema)


@pytest.mark.skip_global_cleanup
Expand Down
4 changes: 2 additions & 2 deletions vllm/v1/attention/backends/rocm_aiter_fa.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.utils.math_utils import cdiv
from vllm.utils.platform_utils import get_cu_count
from vllm.v1.attention.backends.utils import (
AttentionCGSupport,
AttentionMetadataBuilder,
Expand All @@ -31,15 +32,14 @@

if current_platform.is_rocm():
import aiter
from aiter.ops.triton.utils.device_info import get_num_sms

from vllm.triton_utils import tl, triton

def block_size(x, head_dim):
return min(65536 // x.element_size(), triton.next_power_of_2(head_dim))

def num_programs(head_dim):
return min(head_dim, get_num_sms())
return min(head_dim, get_cu_count())

@triton.jit
def cp_mha_gather_cache_kernel(
Expand Down