jl9876andChendi.Xue 0d5d1115d6 [AutoRound] Add offline quantized MXFP4 model support (#5544) ...

Signed-off-by: jl9876 <jia.li@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>

2026-08-25 14:44:38 +00:00

..

tools

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

__init__.py

[Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO (#5910)

2026-08-15 23:01:26 +08:00

_copy_missing_attrs.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

bitsandbytes_config.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

component_config.py

[Bugfix] Fix Qwen3-Omni AWQ quantization name mapping (#5687)

2026-08-23 15:13:36 +00:00

factory.py

[AutoRound] Add offline quantized MXFP4 model support (#5544)

2026-08-25 14:44:38 +00:00

inc_config.py

[MXFP8][XPU] enable mxfp8 using vLLM main repo method (#3782)

2026-05-28 02:47:22 +00:00

int8_config.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

mxfp4_config.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

mxfp8_config.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

quack_fp8.py

[Bugfix][Quant] Skip quack FP8 GEMM when scales are unpopulated (#5262)

2026-07-21 10:11:16 +00:00