kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-26 21:53:30 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,246 Commits 28 Branches 62 Tags 2.3 GiB
a97e411b44
Commit Graph

4246 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Chang Liu
a97e411b44
[https://nvbugs/5747911][fix] Use offline data path for the unit test of mmencoder server (#10135) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-12-18 15:19:23 -08:00
Lizhi Zhou
f02782a6f2
[https://nvbugs/5726066][fix] fix auto-scaling related failures (#9845) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
 2025-12-18 16:37:48 -05:00
Enwei Zhu
6fe89ea00f
[TRTLLM-9819][perf] Reuse alltoall workspace for CuteDSL MoE output (#9840) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-18 10:36:38 -08:00
CarstyYou
0b279f4ad4
[https://nvbugs/5456493][feat] Add fp8 bmm on sm120 (#9687) 
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
 2025-12-18 22:57:20 +08:00
ZhichenJiang
4e55b83101
[None][perf] Add more optimization options for MOE CuteDSL finalized kernel (#10042) 
Signed-off-by: zhichen jiang <zhichenj@NVIDIA.com>
 2025-12-18 22:49:28 +08:00
Nikita Korobov
3b4f26e4d1
[None][feat] update TRT-LLM Gen MoE for NvFp4 + bias with tileN=256 (#9734) 
Signed-off-by: Nikita Korobov <14355239+nekorobov@users.noreply.github.com>
 2025-12-18 11:58:23 +01:00
yuanjingx87
df15be3fad
[None][infra] Fix slurm job does not catch cancelled jobs (#9722) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
Signed-off-by: yuanjingx87 <197832395+yuanjingx87@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-18 00:32:43 -08:00
Bo Li
9d7e038bcb
[https://nvbugs/5753250][infra] Waive _test_openai_responses. (#10110) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-18 00:15:06 -08:00
Emma Qiao
33a90f2dd2
[None][infra] Waive failed cases for main branch on 12/18 (#10105) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-17 21:35:45 -08:00
Yuxian Qiu
bec864a78c
[None][fix] avoid ID conversion for non enable_configurable_moe cases. (#10003) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-18 13:29:52 +08:00
yuanjingx87
897a38978d
[None][infra] Update allowlist 2025.12.17 (#10097) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-12-17 21:11:35 -08:00
Wanli Jiang
601c29ca73
[https://nvbugs/5721644][fix] Update tests for nemotron_h (#9993) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-18 12:38:02 +08:00
Lucas Liebenwein
76ec820465
[#7532][feat] AutoDeploy: gather logits before lm head (#9962) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-17 19:50:13 -08:00
TensorRT LLM
cfe53e7425 [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2025-12-18 03:23:35 +00:00
xinhe-nv
4a98f190a8
[None][chore] Add failed cases into waives.txt (#10025) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-17 19:13:52 -08:00
xinhe-nv
c1cfb61b1b
[TRTLLM-9381][feat] Add kimi k2 fp4 tests (#9906) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-17 18:15:27 -08:00
TensorRT LLM
50c2b82f24 [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2025-12-17 23:45:35 +00:00
tburt-nv
27064f95c7
[None][chore] Clarify copyright header guidance (#9882) 
Signed-off-by: Tyler Burt <195370667+tburt-nv@users.noreply.github.com>
 2025-12-18 06:38:10 +08:00
tburt-nv
5da7879b38
[None][fix] Revert GHA upgrade for blossom-ci workflow (#10095) 
Signed-off-by: Tyler Burt <195370667+tburt-nv@users.noreply.github.com>
 2025-12-17 15:57:04 -05:00
Chenghao Zhang
22c6e8a424
[None][fix] Autodeploy: fix some legacy flashinfer attention test errors (#9928) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-17 12:27:22 -08:00
Salman Chishti
cb5cd4376e
[None][chore] Upgrade GitHub Actions for Node 24 compatibility (#10045) 
Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>
 2025-12-17 09:44:09 -08:00
Yuan Tong
f7e245668b
[TRTLLM-9680][perf] Optimize TRTLLMSampler log_probs performance (Core fix has been merged via #9353) (#9655) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-12-17 17:56:01 +08:00
Yukun He
00c0564334
[None][chore] Remove unnecessary warning log for tuning. (#10077) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 01:51:17 -08:00
Yukun He
18b335d584
[TRTLLM-9989][fix] Disable tvm_ffi for CuteDSL nvFP4 dense GEMM. (#10040) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 00:41:26 -08:00
Yukun He
2fd1a23e4c
[TRTLLM-9998][fix] Change trtllm-gen MoE distributed tuning strategy back to INDEPENDENT (#10036) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 00:35:22 -08:00
yufeiwu-nv
5d71f662c3
[https://nvbugs/5698434][test] Add Qwen3-4B-Eagle3 One-model perf test (#10041) 
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
 2025-12-17 13:37:25 +08:00
Void
47404196fa
[None][fix] Enabled simultaneous support for low-precision combine and MTP. (#9091) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-12-17 13:37:08 +08:00
Emma Qiao
0dbf3948cc
[None][infra] Waive failed tests due to llm model files (#10068) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-16 20:12:57 -08:00
Kaiyu Xie
02fd13448b
[None] [feat] Enhancements to slurm scripts (#10031) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-12-16 19:31:27 -08:00
JunyiXu-nv
6649c3743c
[https://nvbugs/5635153][chore] Remove responses tests from waive list (#10026) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-17 11:22:02 +08:00
shuyixiong
26fb063076
[https://nvbugs/5741060][fix] Fix pg op test (#9989) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-12-17 09:44:25 +08:00
Aurelien Chartier
7175d89b48
[None][fix] Fix iteration stats for spec-dec (#9855) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-12-16 14:11:38 -08:00
QI JUN
dba9036072 [None][doc] remove nano-vl-v2 model support in release notes (#9887) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
QI JUN
3daca4fea3 [https://nvbugs/5729847][doc] fix broken links to modelopt (#9868) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
QI JUN
e6ab864066 [None][doc] Update release notes (#9739) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
Co-authored-by: Laikh Tewari <laikhtewari1@gmail.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
Zac Patel
1ffa2c8937 [IB-1920][doc] Update Perf_Overview.md with Benchmarking Results for Release 1.1 (#9723) 
Signed-off-by: Zachary Patel <22306219+zbpatel@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
xiweny
2756a0da60 [TRTLLM-4629][doc] Add B300 & GB300 in documents (#9663) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
ruodil
07f307d131 [https://nvbugs/5652552][fix] cherry-pick add printing for llm args (#9206) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
Iman Tabrizian
1fc8bd3cd8 [TRTLLM-9082][doc] Address Dynamo Example feedback (#9619) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
Kaiyu Xie
e41b060fe6 [TRTLLM-9090] [doc] Update online benchmarking docs (#9611) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
Lizhi Zhou
bd13957e70
[TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-12-16 05:16:32 -08:00
Enwei Zhu
609d1d0383
[None][fix] Fix Illegal Memory Access for CuteDSL Grouped GEMM (#10008) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-16 04:06:49 -08:00
Enwei Zhu
6a238ca8ad
[None][doc] Update CONTRIBUTING.md (#10023) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-16 18:58:43 +08:00
Emma Qiao
12727ebd7f
[None][infra] Waive failed test for main branch on 12/16 (#10029) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-16 02:54:32 -08:00
Perkz Zheng
064b67e40c
[https://nvbugs/5727952][fix] a pdl bug in trtllm-gen fmha kernels (#9913) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-12-16 00:34:37 -08:00
yuanjingx87
0a4c59136a
[None][infra] Fixing credential loading in lockfile generation pipeline (#10020) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-12-16 15:38:29 +08:00
William Zhang
28b02b4f5a
[None][docs] Add README for Nemotron Nano v3 (#10017) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Co-authored-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-15 22:17:24 -08:00
Yihan Wang
6b5ebaae3e
[None][chore] Update internal_cutlass_kernels artifacts (#9992) 
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
 2025-12-15 21:15:25 -08:00
Wanli Jiang
8af51211c1
[FMDL-1222][feat] Support weight and weight_scale padding for NVFP4 MoE cutlass (#9358) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-16 12:41:17 +08:00
Eran Geva
ce7a42f4cf
[https://nvbugs/5731717][fix] fixed flashinfer build race condition during test (#9983) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-15 20:30:24 -08:00