kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
3,854 Commits 25 Branches 59 Tags 2.1 GiB
4cbfc10b28
Commit Graph

3854 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Yueh-Ting (eop) Chen
4cbfc10b28
[https://nvbugs/5674665][chore] Add test coverage for https://nvbugspro.nvidia.com/bug/5674665 (#9518) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-11-27 21:40:34 +08:00
Bo Li
62b771877c
[TRTLLM-9389][chore] Refactor AlltoallMethodType. (#9388) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-27 21:09:29 +08:00
Fanrong Li
2d5eadf65f
[None][fix] fix TP support for DeepSeek-V3.2 on hopper (#9484) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-27 21:02:25 +08:00
JadoTu
51bf7164d3
[None][feat] add qwen3-next CI test of accuracy on BF16 and NVFP4 (#9330) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-11-27 18:05:00 +08:00
Zhenhuan Chen
e47927e847
[None][fix] change allreduce workspace dtype to torch.int64 to avoid overflow (#9479) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2025-11-27 17:08:41 +08:00
yuanjingx87
3ada0bfc65
[None][infra] Fix Slurm job script (#9508) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-11-27 16:41:01 +08:00
xxi
f1ed057b4c
[cherry-pick][https://nvbugs/5670793][fix] Solve trtllm-serve launch_disaggregated issue (#9346) 
Signed-off-by: xxi <xxi@nvidia.com>
 2025-11-27 16:13:58 +08:00
Emma Qiao
a21be43677
[TRTLLM-9279][infra] Use flexcache for gh200 nodes since they locate in Austin (#9405) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-27 15:42:38 +08:00
Lizhi Zhou
8104a78931
[None][chore] revert batch_size=1 to prevent timeout and lower accuracy reference by 0.12% as a WAR (#9447) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: Shi Xiaowei <39303645+Shixiaowei02@users.noreply.github.com>
 2025-11-27 14:25:44 +08:00
Liao Lanyu
5425d96757
[TRTLLM-9513][docs] Qwen3 deployment guide (#9488) 
Signed-off-by: Lanyu Liao <laliao@laliao-mlt.client.nvidia.com>
Co-authored-by: Lanyu Liao <laliao@laliao-mlt.client.nvidia.com>
 2025-11-27 14:12:35 +08:00
Emma Qiao
0442510304
[None][infra] Waive failed case in pre-merge on 11/27 (#9507) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-27 13:53:33 +08:00
Ziyi Xiong
1dd55d8507
[https://nvbugs/5698581][fix] Init draft tokens for CUDA graph dummy request (#9505) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-11-27 13:05:37 +08:00
Jiagan Cheng
14762e0287
[None][fix] Replace PYTORCH_CUDA_ALLOC_CONF with PYTORCH_ALLOC_CONF to fix deprecation warning (#9294) 
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
 2025-11-27 12:22:01 +08:00
HuiGao-NV
03331bc43d
[https://nvbugs/5547414][fix] enable case after using local cache model (#9473) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-11-27 12:18:20 +08:00
Patrice Castonguay
1b2da426cd
[https://nvbugs/5680310][fix] Fix ctx only timed out test (#9410) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-11-27 11:21:21 +08:00
TensorRT LLM
89701a594b [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2025-11-27 03:19:47 +00:00
QI JUN
a67d94963e
[None][chore] update comments in llm_args.py (#9472) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-27 11:06:34 +08:00
QI JUN
c6fa042332
[TRTLLM-9085][doc] fix math formula rendering issues (#9481) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-27 10:09:12 +08:00
Aurelien Chartier
f2f197360d
[#9463][feat] Add revision option to trtllm commands (#9498) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-11-27 09:30:01 +08:00
Shi Xiaowei
e76e149861
[https://nvbugs/5608930][fix] Fix a typo (#9487) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-11-27 09:05:17 +08:00
Zheyu Fu
dbbed1f85a
[None][ci] Waive blackwell test on spec gate. (#9502) 
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
 2025-11-27 07:19:58 +08:00
Chenghao Zhang
18fbda5cdb
[None][feat] AutoDeploy: Add A_log fusion for Mamba layers (#9422) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-26 14:39:20 -08:00
Chenghao Zhang
bc7b60e016
[None][feat] AutoDeploy: Remove redundant copies in mamba layers (#9461) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-26 14:38:33 -08:00
yuanjingx87
356f67c1cb
[None][infra] Fail the pipeline when slurm ssh dropped (#9157) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-11-26 09:35:04 -08:00
yuanjingx87
d7ef8849d2
[None][infra] Update allowed list 2025.11.25 (#9468) 
Signed-off-by: Yuanjing Xue <197832395+yuanjingx87@users.noreply.github.com>
 2025-11-26 09:32:05 -08:00
Aurelien Chartier
ef7ee6a940
[None][feat] Add environment variable to force spec-dec number of accepted tokens (#9371) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-11-26 07:22:16 -08:00
Chang Liu
b10137fdd5
[None][feat] Support MLA chunked prefill for DeepSeek V3.2 model (#9376) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-11-26 16:38:25 +08:00
Enwei Zhu
1bf2d750a2
[None][chore] Upgrade CuteDSL to 4.3.0 (#9444) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-11-26 14:53:09 +08:00
JunyiXu-nv
b7308a4000
[https://nvbugs/5580099][fix] Cherry pick IMA issue fix from release/1.1 (#9032) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-11-26 13:09:06 +08:00
Wanli Jiang
d100599ea7
[TRTLLM-9264][fix] Add accuracy/unit tests/doc for phi4mm (#9246) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-11-26 11:12:35 +08:00
TensorRT LLM
b04421e5ba [None][infra] Check in most recent lock file from nightly pipeline 
Signed-off-by: TensorRT LLM <90828364+tensorrt-cicd@users.noreply.github.com>
 2025-11-26 03:08:38 +00:00
shuyixiong
d8acea1db3
[TRTLLM-9293][feat] Enable partial weight loading to support streaming update weights (#9224) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-11-26 10:59:06 +08:00
QI JUN
5972119e1c
[None][ci] move some slow test cases of DGX-B200 to post merge (#9467) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-26 10:48:53 +08:00
fredricz-20070104
6a64cb4c71
[TRTLLM-8936][test] Add disagg and wideep multi-node multi-gpu test cases (#9356) 
Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
 2025-11-26 10:34:49 +08:00
Yiqing Yan
1b9edf62c9
[None][chore] Bump version to 1.2.0rc5 (#9455) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-11-26 08:37:53 +08:00
Chuang Zhu
0e9c7f8c07
[https://nvbugs/5685143][fix] avoid cudaFree overlap with cuda graph (#9438) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-11-25 16:20:29 -08:00
Suyog Gupta
e484bec82f
[None][chore] AutoDeploy add multi stream moe pass to default.yaml (#9430) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-25 14:16:13 -08:00
Robin Kobus
32f53910ef
[TRTLLM-909][feat] Overlap context chunks in pipeline parallel mode (#9308) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-25 22:11:51 +01:00
Eran Geva
afc52d7b93
[https://nvbugs/5647400] [fix] Enlarged the AllReduce workspace size to 64MB. Added AllReduce strategy to AD config. (#9145) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-11-25 10:56:07 -08:00
mpikulski
899fda9e47
[TRTLLM-9490][feat] use FlashInfer's top_k_sampling_from_probs (#9457) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-25 18:53:53 +01:00
mpikulski
c5f52ab304
[TRTLLM-8376][feat] top-p optimization (removes redundant softmax) (#9411) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-25 18:46:48 +01:00
Fanrong Li
8da59103d6
[https://nvbugs/5680905][fix] Relax the MMLU accuracy requirement for DS-v3.2 (#9439) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-26 00:32:20 +08:00
Yan Chunwei
1f43dc8174
[None][ci] waive a test (#9458) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-11-25 07:04:20 -08:00
YueWeng
cc336c4abd
[TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-11-25 09:40:55 -05:00
Pengyun Lin
fa61825c74
[None][feat] Support custom chat template for tool calling (#9297) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-11-25 22:07:04 +08:00
Tailing Yuan
51ef0379d2
[None][feat] Add a parser to layer-wise benchmarks (#9440) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-11-25 05:45:16 -08:00
Fanrong Li
c36f144591
[None][chore] Fix trtllm-eval for PyTorchLLM (#9427) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-25 04:49:03 -08:00
Shi Xiaowei
60786574db
[None][fix] Mitigate test timeout issues (#9445) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-11-25 20:17:54 +08:00
Chao Ni
a2d9e6250a
[https://nvbugs/5667922][fix] Update long context evaluation config (#9426) 
Signed-off-by: mni <125171826+baize97@users.noreply.github.com>
 2025-11-25 19:33:38 +08:00
Yueh-Ting (eop) Chen
a38d91aae2
[https://nvbugs/5537996][fix] Let KV cache manager block initialization be aware whether it is doing a dry run or not (#9093) 
Before this commit, the kv cache manager does the same regardless, which causes a mis-calculation in free memory available to allocate for the KV cache manager, hence causing a crash.

This commit fixes this by letting KV cache manager initialization be aware whether it is doing the dry run or not. If it is a dry run, use the max_tokens setting that is already pre-calculated and filled into kv_cache_config.max_tokens.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-11-25 17:27:11 +08:00