4 people 0b37d8389f fix: NVFP4 quantization out_dtype should match model dtype, not torch default (#48861) ...

Signed-off-by: Chris Fontes <2224082+fattchris@users.noreply.github.com>
Co-authored-by: Chris Fontes <chris@fontes.io>
Co-authored-by: Chris Fontes <chris@fontes.dev>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-03 22:47:37 +00:00

..

compressed_tensors

[XPU] [Linear] add torch as xpu linear backend (#49664)

2026-08-03 14:30:21 +08:00

inc

[INC] fix w4a4 model (#50807)

2026-08-03 14:28:58 +08:00

online

[chore] clean-up weight prepack for INT8 MoE (#50116)

2026-07-31 10:15:38 +00:00

quark

[ROCm][Quark][7/N] Use MXFP4 linear kernel abstraction for emulation backend (#48949)

2026-07-31 10:07:15 -07:00

turboquant

[Refactor] Remove dead code (#42889)

2026-05-18 16:41:22 -04:00

utils

[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)

2026-07-31 14:13:03 -07:00

__init__.py

[Quant] Add nvfp4_per_token online MoE quantization (#48538)

2026-07-16 14:25:27 -07:00

auto_awq.py

[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)

2026-07-31 14:13:03 -07:00

auto_gptq.py

[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)

2026-07-31 14:13:03 -07:00

awq_triton.py

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

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

base_config.py

Remove unnecessary load_weights methods (#44589)

2026-06-29 01:52:23 -07:00

bitsandbytes.py

[Bugfix] Convert Gemma4-MM ViT linear layers to vllm native impl (#43798)

2026-06-01 21:41:16 -07:00

experts_int8.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

fbgemm_fp8.py

[ROCm][FEAT] Integrate aiter gemm w8a8 ptpc (#33773)

2026-04-16 09:55:29 +08:00

fp8.py

[Refactor] Remove multiple dead codes (#50285)

2026-08-03 10:59:08 -04:00

fp_quant.py

[Refactor] Remove dead code fp quant (#44122)

2026-06-03 14:22:23 -04:00

humming.py

[Bug][Quantization] Fix humming is_layer_skipped for compressed-tensors "re:" ignore entries (#48507)

2026-07-16 07:47:42 -07:00

input_quant_fp8.py

Remove triton per group quant [ROCm] [Bugfix] (#49621)

2026-07-28 05:53:46 +00:00

kv_cache.py

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

modelopt.py

fix: NVFP4 quantization out_dtype should match model dtype, not torch default (#48861)

2026-08-03 22:47:37 +00:00

moe_wna16.py

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

mxfp4.py

[ROCm][Kimi-K3] aiter moe environment variable cleanup (#50582)

2026-08-03 18:54:04 +00:00

qutlass_utils.py

[CompressedTensors] FP4 Qutlass Integration (#43229)

2026-07-28 20:34:20 -06:00

torchao.py

[Bugfix] Clear error message for FP8 torchao quantization on unsupported GPUs (#36854)

2026-05-22 20:09:17 +00:00