 b8zhong
|
d36f6f043c
|
[Fix] flashinfer_trtllm intermediate_size assertion with Qwen3 + TP=8 (#16824)
|
2026-01-17 09:24:05 +08:00 |
|
|
Baizhou Zhang
|
a04675892e
|
Update flashinfer to 0.6.1 (#15551)
|
2026-01-17 00:48:30 +08:00 |
|
|
b8zhongandBrayden Zhong
|
24b30f7757
|
MoE Refactor: Refactor fp8.py -> flashinfer_trllm.py (#15151)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
|
2026-01-07 15:35:00 -08:00 |
|
|
DarkSharpness
|
f6f7af4068
|
[Refactor] Clean up custom op (#15995)
|
2026-01-01 21:41:56 +08:00 |
|
|
jiaming1130andZhengdQin
|
60a230b1fd
|
[NPU] Support w4a8 with activation clip (#14736)
Co-authored-by: ZhengdQin <46387172+ZhengdQin@users.noreply.github.com>
|
2025-12-27 16:19:46 +08:00 |
|
|
Liangsheng Yin
|
393e2f9b62
|
Revert "[FusedMoE] Fix fused w13 tp sharded weight loading" (#15579)
|
2025-12-22 04:15:24 +08:00 |
|
|
Ke Bao
|
8fe3e37468
|
Support piecewise cuda graph for dsv3 fp4 (#15531)
|
2025-12-21 14:50:32 +08:00 |
|
|
Yinghai Lu
|
fc05acc2c7
|
[FusedMoE] Fix fused w13 tp sharded weight loading (#15432)
|
2025-12-21 13:59:36 +08:00 |
|
|
Khush Gupta
|
ef908aeb40
|
fixed trtllm nvfp4 backend for moe (#15022)
|
2025-12-19 10:49:21 -08:00 |
|
|
Yuwei An
|
9d0347b33a
|
EP Support for Piecewise Cuda Graph (#14164)
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
|
2025-12-20 01:59:27 +08:00 |
|
|
elvischenv
|
9970ee34e8
|
Mistral Large 3 NVFP4 TRTLLM MoE support (#15049)
|
2025-12-18 11:11:42 +08:00 |
|
|
elvischenv
|
435d1c83c1
|
[Perf] Enable Flashinfer autotune by default (#14357)
|
2025-12-16 23:01:39 -08:00 |
|
|
Sam
|
d7ed8a8c24
|
[NVIDIA] Enable TRTLLM BF16 MoE on Blackwell GPUs (#13798)
|
2025-12-11 22:56:13 -08:00 |
|
|
Sam
|
922756aaa1
|
[FIX] trtllm-moe-fp4-renorm for Qwen series models (#14350)
|
2025-12-04 12:52:21 -08:00 |
|
|
|
20aad5b5ab
|
Single Batch Overlap for MoE Models (#9660)
Co-authored-by: Cheng Wan <wan4ch@gmail.com>
Co-authored-by: Zqy11 <841971412@qq.com>
Co-authored-by: AniZpZ <aniz1905@gmail.com>
Co-authored-by: TianyuZhang1214 <tianyuzhang1214@gmail.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
|
2025-12-03 10:07:42 -08:00 |
|
|
Lianmin Zheng
|
ca52ed425f
|
Clean up imports and move files (#14317)
|
2025-12-02 16:31:54 -08:00 |
|
|
|
02af51e4fc
|
Support fp4 fp8 non gated moe (#13794)
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
|
2025-12-01 15:26:28 -08:00 |
|
|
gongwei-130
|
3339c81072
|
fix RuntimeError: RMSNorm failed with error code an illegal memory access was encountered (#14135)
|
2025-11-29 12:17:41 -08:00 |
|
|
SamandKaixi Hou
|
91e8dc371a
|
[Feat][NVFP4] Enable NVFP4 MoE for Qwen series models (eg. Qwen3-Next) #13761 (#13761)
Co-authored-by: Kaixi Hou <kaixih@nvidia.com>
|
2025-11-26 17:53:45 -07:00 |
|
|
LiwansiandEven Zhou
|
432ecf841e
|
[Ascend] qwen optimization (#12078)
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
|
2025-11-25 19:44:24 +08:00 |
|
|
|
b0a26ba624
|
Add support for bf16 x bf16 cutlass fused MoE (#10275)
Co-authored-by: Sam Li <lsam@nvidia.com>
Co-authored-by: jackeyhua <jackeyhuasjtu@gmail.com>
|
2025-11-24 18:49:39 -08:00 |
|
|
Kangyan-Zhou
|
59b4d7f8d6
|
Fix B200 Nightly tests and move one manual test back to unit test to prevent the same issue (#13746)
|
2025-11-21 17:41:12 -08:00 |
|
|
Shu Wang
|
a56f770277
|
Fix global scaling factor loading hang (#13484)
|
2025-11-21 16:07:06 -08:00 |
|
|
roikoren755
|
1b48e1b974
|
Feat/nemotron nano v3 support (#12690)
|
2025-11-21 13:53:05 -08:00 |
|
|
Cheng WanandBaizhou Zhang
|
6d0e0b9bfc
|
[11/N] MoE Refactor: Simplifying SBO Implementation with Dispatcher Hooks (#13327)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2025-11-21 01:11:37 -08:00 |
|
|
Qiaolin YuandKangyan-Zhou
|
78a4b446c6
|
Fix dpsk-r1-fp4 tp8 by reverting two commits (#13162 and #13341) (#13348)
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
|
2025-11-15 21:31:36 -08:00 |
|
|
Vincent Zhong
|
0d116b9a0b
|
Clean up deprecated tile_tokens_dim for next flashinfer (#13341)
Signed-off-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
|
2025-11-16 00:50:15 +08:00 |
|
|
Morpheus Guoandyuechguo
|
e7b57b0d04
|
[BugFix] weight load bug when checkpoint expert.gate and exepert.up_proj are not fused (#13113)
Co-authored-by: yuechguo <yuechguo@amd.com>
|
2025-11-14 00:35:44 -08:00 |
|
|
Sam
|
e7e89349c9
|
Enable Flashinfer TRTLLM-GEN-MoE FP8 blockwise kernel for Qwen3-Next on Blackwell (#12543)
|
2025-11-13 19:44:44 +08:00 |
|
|
|
aead0ef5e5
|
[FEAT][ROCM] enable fused shared expert for Rocm (#12201)
Co-authored-by: ZLkanyo009 <4071250045@qq.com>
Co-authored-by: HAI <hixiao@gmail.com>
|
2025-11-13 00:41:40 -08:00 |
|
|
Shu Wang
|
7aa443903d
|
Fix nan in global scaling factor for large scale nvfp4 EP (#13162)
|
2025-11-12 15:32:23 -08:00 |
|
|
|
ddd1440d0f
|
Refactor KTransformers heterogeneous compute with unified GPU-quantization backend (#12834)
Co-authored-by: Chen Hongtao <56470055+chenht2022@users.noreply.github.com>
Co-authored-by: chenht2022 <cht22@mails.tsinghua.edu.cn>
Co-authored-by: skqliao <skqliao@gmail.com>
Co-authored-by: ovowei <1913953267@qq.com>
|
2025-11-09 21:06:32 -08:00 |
|
|
elvischenv
|
1fa788ec14
|
[Bugfix] Fix illegal memory access (#12758)
|
2025-11-06 21:59:57 -08:00 |
|
|
Nicolas Castet
|
2340798353
|
Register allgather/reducescatter buffers with symm memory (#12572)
|
2025-11-04 17:11:36 -08:00 |
|
|
Trevor Morris
|
dbcf85b7f0
|
Add --speculative-moe-runner-backend server arg (#10183)
|
2025-11-04 00:20:56 -08:00 |
|
|
Lianmin ZhengandNicolas Castet
|
7a21d8b276
|
Reduce the overhead of nccl symmetric memory (#12524)
Co-authored-by: Nicolas Castet <ncastet@nvidia.com>
|
2025-11-03 11:56:27 -08:00 |
|
|
Cheng Wan
|
649949807f
|
[10/N] MoE Refactor: reorganize deepgemm runner in DeepEPMoE (#12054)
|
2025-10-24 19:16:17 -07:00 |
|
|
b8zhong
|
f80371ff8c
|
Use flashinfer_trtllm moe runner backend to gain around 10% perf on b200 fp8 dpsk (#11816)
|
2025-10-23 19:12:15 -07:00 |
|
|
Jonah Bernard
|
62eff37ba1
|
Refactor Triton-kernel MoE runner integration (#11795)
|
2025-10-23 18:47:28 -07:00 |
|
|
jiahanc
|
eec9e471ca
|
[NVIDIA] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#11563)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
|
2025-10-22 13:11:16 -07:00 |
|
|
Xun Sun
|
e028af6998
|
Fix mooncake dispatcher (#11908)
|
2025-10-22 01:11:49 -07:00 |
|
|
AtreamandJianwei Dong
|
7e6191c098
|
init support for KTransformers Heterogeneous Computing (#11487)
Co-authored-by: Jianwei Dong <1913953267@qq.com>
|
2025-10-21 00:17:02 -07:00 |
|
|
Cheng Wan
|
bfc3b3f786
|
[9/N] MoE Refactor: cleanup dispatcher interfaces (#11847)
|
2025-10-20 10:11:46 -07:00 |
|
|
fzyzcjy
|
505329cab0
|
Support shared experts overlap in cutlass moe (#11611)
|
2025-10-18 07:59:40 +08:00 |
|
|
Chang Su
|
627974405d
|
[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)
|
2025-10-17 16:49:46 -07:00 |
|
|
Liangsheng Yin
|
516738b096
|
Depreate global_server_args_dict (#11528)
|
2025-10-13 19:34:43 +08:00 |
|
|
Cheng Wan
|
1bdd010291
|
Revert "Deprecate global_server_args_dict" (#11520)
|
2025-10-12 17:40:40 -07:00 |
|
|
Liangsheng Yin
|
1083e7e3df
|
Deprecate global_server_args_dict (#11331)
|
2025-10-13 01:20:47 +08:00 |
|
|
Cheng Wan
|
3c06b673af
|
[8/N] MoE Refactor: deprecate EPMoE (#11211)
|
2025-10-07 21:51:41 -07:00 |
|
|
Bowen Bao
|
cd4b39a900
|
[quantization] Properly ignore quantization for layers excluded in quant_config (#11205)
|
2025-10-07 14:06:05 -07:00 |
|