kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-04 02:02:01 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,681 Commits 28 Branches 65 Tags 2 GiB
4f86c5f5ce
Commit Graph

4681 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kaiyu Xie
4f86c5f5ce
[None] [feat] Support multiple accuracy tasks for slurm scripts (#10500) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
Co-authored-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2026-01-16 15:50:32 +08:00
dongfengy
6dfb8d7084
[None][fix] Fix Piecewise Cuda Graph for GPTOSS (#10631) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2026-01-16 15:47:34 +08:00
xinhe-nv
0256c7234f
[None][chore] Remove closed bugs (#10586) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-16 15:04:11 +08:00
jmydurant
b163e66182
[None][doc] update doc (add minimax model) (#10746) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2026-01-16 14:54:52 +08:00
Necofish
03cdf5804f
[None][fix] impl fused triton kernel for e8m0 resmooth to reduce memory footprint (#10327) 
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
Co-authored-by: Kanghwan <861393+karljang@users.noreply.github.com>
 2026-01-15 22:13:18 -08:00
Yukun He
f001c4946d
[https://nvbugs/5782112][fix] Fix hanging issue for MNNVL Allreduce under PP (#10633) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-16 13:03:36 +08:00
Emma Qiao
e2c3373749
[None][infra] Waive failed cases for main branch on 01/16 (#10738) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-16 12:46:35 +08:00
Bo Li
7686fbbcbe
[https://nvbugs/5810940][chore] Update waive lists for nvbugs/5810940. (#10737) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2026-01-16 12:08:14 +08:00
Chuang Zhu
8257b67ea5
[https://nvbugs/5791936][fix] Add warning for gen-only paused (#10664) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2026-01-16 11:18:24 +08:00
TensorRT LLM
6541e41c74 [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2026-01-16 03:13:42 +00:00
Enwei Zhu
7b8b9ccbaf
[https://nvbugs/5669671][fix] Support GuidedDecoder with sharded logits (#10698) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-16 11:04:26 +08:00
Enwei Zhu
9f741fb254
[https://nvbugs/5800521][ci] Move test_openai_chat_guided_decoding to H100 stage (to avoid potential OOM) (#10703) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-16 10:42:52 +08:00
xxi
ce561b6a8e
[TRTLLM-9111][feat] MoE test refactor: Extend MoE quantization test utilities with comprehensive quant algorithm support (#10691) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-16 10:26:33 +08:00
Chuang Zhu
7e2cbc0756
[https://nvbugs/5598674][fix] enable partial reuse in gemma and gpt oss test (#10559) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2026-01-16 10:26:15 +08:00
heyuhhh
e3f27e06c7
[None][chore] Waive star attention unittests (#10439) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2026-01-16 10:12:32 +08:00
Yuxian Qiu
ef838cc852
[https://nvbugs/5701445][chore] isolate test. (#10444) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-16 10:04:12 +08:00
Lucas Liebenwein
49c6f73554
[None][bug] AutoDeploy: fix regression in kv cache resize memory estimation (#10726) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-16 09:52:03 +08:00
Iman Tabrizian
5ad8cf6d5e
[https://nvbugs/5738168][fix] unwaive test accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype[False] (#10584) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2026-01-16 06:04:45 +08:00
Thor Johnsen
0998a7bf20
[https://nvbugs/5721661][fix] Prevent out-of-bounds read (#9879) 
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
 2026-01-15 10:51:40 -06:00
heyuhhh
dfac07c045
[None][feat] Support to export data in trtllm-eval (#10075) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2026-01-15 23:27:08 +08:00
forrestl
43b9db3364
[None][doc] doc updates (#10711) 
Signed-off-by: forrestl
 2026-01-15 21:46:49 +08:00
Lizhi Zhou
93db0d5e18
[TRTLLM-9942][feat] new request states and kvcache transceiver APIs in generation-first disagg (#10406) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-15 19:18:21 +08:00
Jun Yang
3bc17e1aa3
[None][doc] doc updates (#10704) 
Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com>
 2026-01-15 19:05:26 +08:00
Lizhi Zhou
ff277b591e
[https://nvbugs/5791830][fix] fix pp loop hang caused by i-sending new requests (#10665) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-15 16:33:55 +08:00
yufeiwu-nv
cd55fb4551
[None][test] Remove NIM test (#10657) 
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
 2026-01-15 16:30:47 +08:00
Pengbo Wang
683515b1bd
[None][feat] Use XQA JIT impl by default and mitigate perf loss with sliding window (#10335) 
Signed-off-by: Pengbo Wang <221450789+pengbowang-nv@users.noreply.github.com>
 2026-01-15 15:47:00 +08:00
Perkz Zheng
71ccc07d2b
[None][feat] update trtllm-gen to support groupsTokensHeadsQ (#10261) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2026-01-15 02:24:25 -05:00
Ludwig Schneider
e12a7119cf
[https://nvbugs/5741392][fix] [chore] Remove test exemptions from waivers tile (#10517) 
Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>
 2026-01-14 22:07:52 -08:00
Yiqing Yan
f4ace99218
[None][chore] Bump version to 1.3.0rc0 (#10681) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2026-01-15 13:55:44 +08:00
ruodil
22240e43eb
[None][test] store per user output and per gpu output metric in csv file (#10658) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
 2026-01-15 00:51:08 -05:00
Emma Qiao
7b3b6f1161
[None][infra] Waive failed tests on main 01/15 (#10683) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-15 13:40:37 +08:00
Anish Shanbhag
faa80e73fd
[None][feat] Auto download speculative models from HF for pytorch backend, add speculative_model field alias (#10099) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2026-01-14 21:06:07 -08:00
Lucas Liebenwein
62050b2381
[None][infra] separate AutoDeploy tests into own stages (#10634) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-14 23:05:26 -05:00
Void
f7de285a82
[None][fix] add quantization check for DeepEP LL low precision combine in new moe comm api (#10072) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2026-01-14 22:15:29 -05:00
TensorRT LLM
482b7b8837 [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2026-01-15 03:10:09 +00:00
Lucas Liebenwein
15b43e8a14
[https://nvbugs/5777041][fix] fix AutoDeploy ep sharding test (#10460) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-14 21:53:56 -05:00
Dom Brown
94c7b69048
[https://nvbugs/5630196] [fix] Prevent flaky failures in C++ test_e2e.py by using local cached datasets for benchmarking (#10638) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2026-01-14 21:39:55 -05:00
Wanli Jiang
73d1840c12
[TRTLLM-10245][feat] Add accuracy tests for super v3 fp8 model (#10482) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2026-01-15 10:07:02 +08:00
dominicshanshan
0f2d61b8c6
[https://nvbugs/5766952][fix] Fix AIPerf issue. (#10666) 
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-15 09:54:34 +08:00
bhsueh_NV
5f9fc50233
[https://nvbugs/5800725][infra] Update waives.txt (#10625) 2026-01-15 09:08:07 +08:00
彭晋韬(jtao peng)
211c44b951
[None][feat] Adding torch ext API for FusedAddRMSNormQuant kernel (#9905) 
Signed-off-by: jintaop <jintaop@nvidia.com>
 2026-01-15 07:29:15 +08:00
TensorRT LLM
968db53194 [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2026-01-14 22:18:53 +00:00
Tzu-Ling Kan
c99faaed06
[#9760][fix] Use RequestError for validation errors to prevent engine shutdown (#9761) 
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
 2026-01-14 10:22:36 -05:00
Emma Qiao
01083b56bf
[TRTLLM-9849][infra] Update dependencies to 25.12 (#9818) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
Signed-off-by: xxi <xxi@nvidia.com>
Signed-off-by: xxi <95731198+xxi-nv@users.noreply.github.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: xxi <xxi@nvidia.com>
Co-authored-by: xxi <95731198+xxi-nv@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-14 21:54:04 +08:00
Emma Qiao
35c24424f6
[None][infra] Waive failed cases in post-merge on 01/14 (#10668) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-14 21:39:32 +08:00
HuiGao-NV
b10704428d
[https://nvbugs/5787566][fix] Only keep a limited number of performance statistic data (#10569) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2026-01-14 07:53:01 -05:00
Bo Li
582dec5bb5
[https://nvbugs/5774869][infra] Use 2 GPUs to test skip softmax attention on H100. (#10420) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2026-01-14 07:03:01 -05:00
shuyixiong
babd5ecacc
[https://nvbugs/5760740][fix] Enable ray tests (#10272) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2026-01-14 19:25:46 +08:00
Kyungmin Lee
25148d3fee
[None][feat] Support new Transformers RoPE configuration format (#10636) 
Signed-off-by: lkm2835 <lkm2835@gmail.com>
 2026-01-14 19:41:27 +09:00
xxi
e9817461ba
[None][chore] improve the readability of log for cutlass can only sup… (#10630) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-14 05:33:45 -05:00