Search results

lora parameters have no attributes named weight or bias

Status: Open.

#31 In LeanModels/DFloat11;

· pnaclcu opened on Oct 17, 2025

qwen-image-edit load error

Status: Open.

#29 In LeanModels/DFloat11;

· Luwill6 opened on Sep 19, 2025

How to compress t5-v1_1-xxl and Gemma-2-2B?

Status: Open.

#28 In LeanModels/DFloat11;

· mingyi456 opened on Sep 14, 2025

Pls support ComfyUI

Status: Open.

#23 In LeanModels/DFloat11;

· EidosL opened on Aug 5, 2025

Can we quantize the df11 model ourselves?

Status: Open.

#22 In LeanModels/DFloat11;

· win10ogod opened on Aug 5, 2025

DFloat request — Qwen-Image

Status: Open.

#21 In LeanModels/DFloat11;

· kabachuha opened on Aug 4, 2025

The CUDA version is 12.0, and running dfloat11 will result in an error.

Status: Open.

#19 In LeanModels/DFloat11;

· Fu-Fu-Fu-Fu opened on Jul 8, 2025

wani2v please?

Status: Open.

#17 In LeanModels/DFloat11;

· animemory opened on Jun 2, 2025

Questions on the Huffman Tree in Fig.2

Status: Open.

#16 In LeanModels/DFloat11;

· Andy0422 opened on May 28, 2025

Can it be compatible with other quantization models such as fp8, int4, and models like Gapeleon/bytedance-BAGEL-7B-MoT-INT8 to reduce their memory usage

Status: Open.

#15 In LeanModels/DFloat11;

· libai-lab opened on May 25, 2025

CUDA kernel source code

Status: Open.

#12 In LeanModels/DFloat11;

· amosyou opened on May 10, 2025

fine-tuning

Status: Open.

#10 In LeanModels/DFloat11;

· nanaj96 opened on May 8, 2025