iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
8,162 Commits 3 Branches 0 Tags
3e36fcbee642f41278a4881c9e2bfbbd7c28e607
Commit Graph
434 Commits
Author SHA1 Message Date
Po-Han Huang (NVIDIA) ff08e51940 [NVIDIA] Fix Llama4 Scout FP4 functionality issues (#21499) 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
 2025-07-30 07:33:40 -07:00
Wenhua Cheng ad341c5194 [Bugfix]fix mixed bits and visual language model quantization in AutoRound (#21802) 
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
 2025-07-29 07:26:31 -07:00
Wentao Ye 48b763d6b5 [Refactor] Merge Compressed Tensor FP8 CompressedTensorsW8A8Fp8MoEMethod and CompressedTensorsW8A8Fp8MoECutlassMethod (#21775) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-28 19:47:21 -06:00
Nikhil Guptaandmgoin 89ac266b26 [Feat]: Add support for Dynamic Quant 4 bit CPU kleidiai kernels (#17112) 
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-28 20:55:15 +00:00
TJian e626d286f5 [FEAT] [ROCm] [AITER]: Add AITER HIP block quant kernel (#21242) 2025-07-28 05:07:06 +00:00
Wentao Ye bda9d0535f [Refactor] Refactor MOE NVFP4 Code Base: ModelOpt + Compressed Tensor (#21631) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-27 05:25:21 -07:00
Alex Kogan 7ae75fa6d0 [Feature] Add support for MoE models in the calibration-free RTN-based quantization (#20766) 
Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
 2025-07-25 18:09:34 -07:00
Wentao Ye 75d29cf4e1 [Perf] Cuda Kernel for Int8 Per Token Group Quant (#21476) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-25 17:07:07 -07:00
Wentao Ye 633f6e804b [Bug] Fix DeepGemm Init Error (#21554) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-24 20:07:22 -07:00
Shu Wang 1b25f1fe75 Update flashinfer CUTLASS MoE Kernel (#21408) 
Signed-off-by: Shu Wang. <shuw@nvidia.com>
 2025-07-24 08:13:31 -07:00
Wentao Ye 774d0c014b [Perf] Cuda Kernel for Per Token Group Quant (#21083) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-22 07:27:15 -07:00
Duncan Mossjiahancmgoin
 		2c8db17cfd [feat]: add SM100 support for cutlass FP8 groupGEMM (#20447) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-22 07:27:12 -07:00
Mickaël Seznecandmgoin 4fb56914c5 [perf] Add fused MLA QKV + strided layernorm (#21116) 
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-22 07:07:44 -07:00
Ming Yang e7b2042681 Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-07-21 21:49:01 -07:00
Zhiyu 6b46c4b653 Add Nvidia ModelOpt config adaptation (#19815) 
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
 2025-07-21 10:02:58 -04:00
Kaixi Houandmgoin 6d0734c562 [NVIDIA] Add SM100 Flashinfer MoE blockscale fp8 backend for low latency (#20645) 
Signed-off-by: kaixih <kaixih@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-19 02:33:01 -07:00
Shu Wangandmgoin c7d8724e78 [Core] FlashInfer CUTLASS fused MoE backend (NVFP4) (#20037) 
Signed-off-by: shuw <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-17 21:32:45 -07:00
ElizaWszola 9fb2d22032 [Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
 2025-07-17 09:56:44 -04:00
Michael Goin 28a6d5423d [Bugfix] Fix Machete zero point issue for GPTQ models on SM90 (#21066) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-16 19:54:45 -07:00
Nir DavidandUri Livne 01513a334a Support FP8 Quantization and Inference Run on Intel Gaudi (HPU) using INC (Intel Neural Compressor) (#12010) 
Signed-off-by: Nir David <ndavid@habana.ai>
Signed-off-by: Uri Livne <ulivne@habana.ai>
Co-authored-by: Uri Livne <ulivne@habana.ai>
 2025-07-16 15:33:41 -04:00
Wentao Ye 76ddeff293 [Doc] Remove duplicate docstring (#21012) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-15 20:09:13 -07:00
Ming Yang fcb9f879c1 [Bugfix] Correct per_act_token in CompressedTensorsW8A8Fp8MoECutlassM… (#20937) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-07-15 19:53:42 -07:00
Ruheena Suhani Shaik 016b8d1b7f Enabled BnB NF4 inference on Gaudi (#20172) 
Signed-off-by: Ruheena Suhani Shaik <rsshaik@habana.ai>
 2025-07-14 20:26:08 -07:00
XiongfeiWei d4170fad39 Use w8a8 quantized matmul Pallas kernel (#19170) 
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
 2025-07-15 03:06:33 +00:00
Michael Goin bcdfb2a330 [Bugfix] Fix incorrect dispatch for CutlassBlockScaledGroupedGemm and DeepGEMM (#20933) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-15 01:42:17 +00:00
TJian 80d38b8ac8 [V1] [ROCm] [AITER] Upgrade AITER to commit 916bf3c and bugfix APIs (#20880) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-07-13 15:19:32 +00:00
ElizaWszola 3b3b778d4a [Bugfix] Fix a couple PPLX+CUTLASS MoE bugs (#20825) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
 2025-07-12 19:39:14 -07:00
Wentao Ye 42d440c22b [Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-12 19:38:45 -07:00
Michael Goin 6e2c176e1f [Bugfix] Restrict Machete to only run on Hopper (#20830) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-12 17:34:40 +00:00
Zhiyu 4afe687a82 Enable ModelOpt Llama4 fp8 checkpoint deployment (#20419) 
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
 2025-07-11 23:07:16 -07:00
Li, Jiang b1235c3e10 [Bugfix] Lazy import fused_experts in BitsAndBytesMoEMethod to avoid break not-cuda-alike devices (#20822) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-07-11 20:52:05 -07:00
Jee Jee Li 8020e98c9f [Quantization][1/N] MoE support BNB-Inflight Quantization (#20061) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-11 08:01:13 +00:00
Luka Govedičandmgoin 31d5c1797f [Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830) 
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-11 04:56:28 +00:00
Wentao Ye e2de455c34 [Feature] Integrate SM100 DeepGEMM support (#20087) 2025-07-10 20:18:05 -07:00
fxmarty-amdandBowen Bao 332d4cb17b [Feature][Quantization] MXFP4 support for MOE models (#17888) 
Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>
 2025-07-09 13:19:02 -07:00
Jacob Manning bf03ff3575 [Kernel] Add Conch backend for mixed-precision linear layer (#19818) 
Signed-off-by: Jacob Manning <jmanning+oss@stackav.com>
 2025-07-09 13:17:55 -07:00
Michael Goin 31b96d1c64 Support Llama 4 for cutlass_moe_fp4 (#20453) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-09 15:53:38 -04:00
Ming Yang c438183e99 [Bugfix] Fix topk_ids indices_type for CUTLASS w8a8 FP8 MoE (#20166) 
Signed-off-by: Ming Yang <yming@meta.com>
 2025-07-08 23:10:57 +00:00
Lucia FangandLucia Fang 8aeaa910a2 Fix unknown attribute of topk_indices_dtype in CompressedTensorsW8A8Fp8MoECutlassMethod (#20507) 
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
 2025-07-05 14:03:20 +08:00
Duncan MossandDuncan Moss 3d184b95b8 [feat]: CUTLASS block scaled group gemm for SM100 (#19757) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>
 2025-07-04 12:58:04 -06:00
Michael Goin 0e3fe896e2 Support Llama 4 for fused_marlin_moe (#20457) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-04 07:55:10 +00:00
Jee Jee Li 1caca5a589 [Misc] Add SPDX-FileCopyrightText (#20428) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-04 07:40:42 +00:00
bnellnm 78fe77534b [Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-07-03 14:55:40 -07:00
Jee Jee Li 1819fbda63 [Quantization] Bump to use latest bitsandbytes (#20424) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-03 21:58:46 +08:00
Li, Jiang 0ec3779df7 [Bugfix][CI/CD][CPU] Fix CPU CI tests (#20383) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-07-02 20:11:36 -07:00
bnellnm 2e25bb12a8 [Bugfix] Fix import of CutlassExpertsFp8 in compressed_tensors_moe.py (#20381) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-07-03 02:07:43 +00:00
bnellnmandElizaWszola c1909e7e8c [Kernels] MoE refactor (#19636) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
 2025-07-02 06:08:27 -07:00
czhu-cohere 3abfe22154 Enable group size 64 for Machete (#20290) 
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
 2025-07-01 18:05:44 -07:00
TJian 02cabff207 [V1] [ROCm] Enable EP with AITER Fused MoE (#20270) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-07-01 16:48:30 +00:00
Kyle Sayers 9025a9a705 [Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046) 2025-07-01 19:20:34 +09:00