3 people 7d6917bef5 [ROCm] Fix MoE kernel test failures on gfx950 (#37833) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>

2026-03-25 13:46:40 -05:00

..

compressed_tensors

[Sparse24] [Deprecation] Remove Sparse24 CT integration and kernels (#36799)

2026-03-23 16:03:29 -04:00

quark

[ROCm] Fix MoE kernel test failures on gfx950 (#37833)

2026-03-25 13:46:40 -05:00

utils

[ROCm] Fix MoE kernel test failures on gfx950 (#37833)

2026-03-25 13:46:40 -05:00

__init__.py

[Quantization][Deprecation] Remove PTPC FP8 (#32700)

2026-03-21 22:10:16 +00:00

awq_marlin.py

[Bugfix] Add replacement of _compute_slot_mapping_kernel on CPU (#37987)

2026-03-24 07:00:20 -07:00

awq_triton.py

…

awq.py

Revert "Consolidate AWQ quantization into single awq_marlin.py file" (#37768)

2026-03-21 17:20:41 -04:00

base_config.py

[Quantization] - Added uses_meta_device_weights to quant config (#34645)

2026-02-17 23:43:44 -08:00

bitsandbytes.py

[ROCm] Enable bitsandbytes quantization support on ROCm (#34688)

2026-02-21 00:34:55 -08:00

cpu_wna16.py

[Torch 2.11] Guard torch._C._cpu attribute checks for forward compatibility (#35673)

2026-03-17 18:47:59 +00:00

experts_int8.py

[MoE Refactor] Introduce MoERunner abstraction and move execution logic from FusedMoE to DefaultMoERunner (#32344)

2026-02-10 19:51:07 -05:00

fbgemm_fp8.py

[FP8]add FP8 WoQ kernel abstraction. (#32929)

2026-03-23 09:47:47 +00:00

fp8.py

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

fp_quant.py

…

gguf.py

[Refactor] Replace activation: str with MoEActivation enum (#33843)

2026-02-11 17:29:32 -08:00

gptq_marlin.py

[Refactor] [1/N] Reorganize kernel abstraction directory (#34055)

2026-02-24 06:47:22 +00:00

gptq.py

…

inc.py

[XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379)

2026-02-02 22:46:10 -08:00

input_quant_fp8.py

[XPU] support MLA model on Intel GPU (#37143)

2026-03-25 17:43:42 +08:00

kv_cache.py

…

modelopt.py

[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)

2026-03-16 18:07:39 -04:00

moe_wna16.py

[Refactor] Replace activation: str with MoEActivation enum (#33843)

2026-02-11 17:29:32 -08:00

mxfp4.py

[Bugfix][ROCm][MoE] Fix mxfp4 oracle regressions from #37128 (#37787)

2026-03-25 08:17:33 +08:00

mxfp8.py

[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)

2026-03-16 18:07:39 -04:00

petit.py

…

qutlass_utils.py

…

schema.py

…

torchao.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00