Rohan PotdarandAndreas Karatzas 0e9358c11d {ROCm]: gpt-oss fusion/padding fixes (#38043) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

2026-03-27 12:19:15 -04:00

..

configs

[AMD][QWEN3-NEXT] FP8 Tunings (#32042)

2026-01-27 09:34:13 +00:00

__init__.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

allspark_utils.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

flashinfer_fp4_moe.py

[Refactor] Move FusedMoE hidden_size roundup to quant_method (#34285)

2026-03-26 23:38:26 -07:00

flashinfer_mxint4_moe.py

[Hardware][SM100] Add TRTLLM Kernel for INT4 W4A16 Kernel. (#32437)

2026-01-30 10:30:46 -08:00

flashinfer_utils.py

[Refactor] Move FusedMoE hidden_size roundup to quant_method (#34285)

2026-03-26 23:38:26 -07:00

fp8_utils.py

[Bugfix] Fix DeepGemm E8M0 accuracy degradation for Qwen3.5 FP8 on Blackwell (#38083)

2026-03-26 01:21:47 -07:00

gptq_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

int8_utils.py

[Bugfix][Quantization] Ensure input contiguity in per_token_quant_int8 (#31637)

2026-01-10 12:40:02 -08:00

layer_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

machete_utils.py

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

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

marlin_utils_fp4.py

[MoE Refactor] Mxfp4 oracle rebased (#37128)

2026-03-21 03:37:04 +00:00

marlin_utils_fp8.py

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

marlin_utils_test.py

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

2025-11-29 07:19:33 -08:00

marlin_utils.py

[ROCm][Refactor] Enable AWQMarlinConfig on ROCm to use choose_mp_linear_kernel (#36505)

2026-03-23 15:36:08 +08:00

mxfp4_utils.py

{ROCm]: gpt-oss fusion/padding fixes (#38043)

2026-03-27 12:19:15 -04:00

mxfp6_utils.py

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

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

mxfp8_utils.py

Integrate flashinfer mm_mxfp8 in ModelOpt MXFP8 (#35053)

2026-02-24 08:45:13 -07:00

nvfp4_emulation_utils.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

nvfp4_utils.py

[UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806)

2026-03-12 05:19:35 -04:00

ocp_mx_utils.py

[ROCm][Quantization] GPT_OSS in amd-quark format model loading and emulations (#29008)

2026-02-10 10:08:05 -05:00

petit_utils.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

quant_utils.py

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

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

w8a8_utils.py

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

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