Michael Goin f9a4087182 Remove weight_scale.T special case for SM90 Block FP8 CUTLASS kernel (#28431) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2025-11-11 11:46:04 -05:00

..

configs

…

__init__.py

…

allspark_utils.py

…

bitblas_utils.py

…

flashinfer_fp4_moe.py

Flashinfer_CUTLASS_MOE fuses quantization for TP (#27223)

2025-10-31 17:54:29 +00:00

flashinfer_utils.py

[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492)

2025-11-10 12:34:57 -05:00

fp8_utils.py

Remove weight_scale.T special case for SM90 Block FP8 CUTLASS kernel (#28431)

2025-11-11 11:46:04 -05:00

gptq_utils.py

…

int8_utils.py

…

layer_utils.py

…

machete_utils.py

…

marlin_utils_fp4.py

…

marlin_utils_fp8.py

…

marlin_utils_test_24.py

…

marlin_utils_test.py

…

marlin_utils.py

…

mxfp4_utils.py

[amd][gptoss] Perf gain because of block alignment (#28024)

2025-11-07 05:27:42 +00:00

mxfp6_utils.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

mxfp8_utils.py

[Bugfix] Fix gpt-oss w4a8 DP/EP on B200 (#26729)

2025-10-21 01:51:14 -04:00

nvfp4_emulation_utils.py

…

nvfp4_moe_support.py

…

ocp_mx_utils.py

…

petit_utils.py

…

quant_utils.py

[Quantization] Automatically infer AWQ modules_to_not_convert field (#26909)

2025-10-21 01:49:28 +00:00

w8a8_utils.py

[RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490)

2025-11-10 08:20:53 -08:00