Dakai Anandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 71bc19dbdd [Bugfix] Fix MoE model load OOM in FlashInfer_TRTLLM backend with sleep mode (#45589) ...

Signed-off-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-06-16 19:36:51 -07:00

..

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

Deprecations for v0.23 and v0.24 (#44992)

2026-06-11 14:35:38 +00:00

flashinfer_mxint4_moe.py

[Bugfix] FlashInfer MXINT4 MoE crashes, missing do_finalize (#39315)

2026-04-08 20:36:33 -04:00

flashinfer_utils.py

[Bugfix] Fix MoE model load OOM in FlashInfer_TRTLLM backend with sleep mode (#45589)

2026-06-16 19:36:51 -07:00

fp8_utils.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

gptq_utils.py

Revert "[MoE Refactor] Migrate MoeWNA16Method quantization to MK orac… (#44033)

2026-05-29 16:45:29 -07:00

humming_utils.py

[Bugfix] Lazily import the humming quantization backend (#44921)

2026-06-10 06:06:17 -07:00

int8_utils.py

Enable perf_token_group_quant/_C_stable_libtorch for ROCm (#42758)

2026-06-02 23:23:28 -07:00

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

[Kernel] Consolidate Marlin thread-tile padding across all dense Marlin paths (#45295)

2026-06-12 13:46:21 -07:00

marlin_utils_fp8.py

[Kernel] Consolidate Marlin thread-tile padding across all dense Marlin paths (#45295)

2026-06-12 13:46:21 -07:00

marlin_utils_test.py

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

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

marlin_utils.py

[Kernel] Consolidate Marlin thread-tile padding across all dense Marlin paths (#45295)

2026-06-12 13:46:21 -07:00

mxfp4_utils.py

[ROCm][gpt-oss] Hybrid CDNA4 swizzle gate for A8W4 MoE (#44804)

2026-06-09 23:59:44 -07:00

mxfp6_utils.py

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

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

mxfp8_utils.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

nvfp4_emulation_utils.py

[NVFP4][Hopper/AMD Instinct] Add Triton kernels for NVFP4 dequantization and QDQ emulation (#40033)

2026-04-30 17:35:48 -04:00

nvfp4_utils.py

[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (#39129)

2026-04-09 15:05:36 -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

quant_utils.py

[Refactor] Remove Fp8OnlineLinearMethod as scheduled (#45463)

2026-06-16 04:35:58 -07:00

w8a8_utils.py

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

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