Commit Graph

2375 Commits

Author SHA1 Message Date
Yan Chunwei
93392cefd2
[None][doc] add Llama PP known issue to release note (#7959)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-24 13:39:54 +02:00
Guoming Zhang
ae8270b713
[None][doc] fix invalid links in perf benchmarking. (#7933)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-23 08:18:17 -07:00
Guoming Zhang
57079cecb3
[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-22 10:05:47 -07:00
QI JUN
68b7900a1d
[https://nvbugs/5531963][fix] cherry pick #7725 (#7907)
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
2025-09-22 06:55:05 -07:00
Yan Chunwei
bc4136ffe7
[https://nvbugs/5427043][fix] cherrypick: request length exceeds max_num_tokens (#7718)
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
2025-09-22 03:37:48 -07:00
Yan Chunwei
ce6ebf695c
[None][fix] api stability bug in status label (#7861)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-21 23:17:26 -07:00
Yan Chunwei
8fecc0645d
[None][doc] add stable label to all the un-labelled arguments in LLM class (#7863)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-21 22:47:36 -07:00
Zac Patel
b280c1620f
[None][doc] Update Perf-Overview.md for release/1.0 (#7848)
Signed-off-by: zpatel <22306219+zbpatel@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
2025-09-22 13:38:16 +08:00
Yan Chunwei
4f6e14cb2c
[None][doc] add a guide for modifying APIs (#7866)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-22 13:33:46 +08:00
Guoming Zhang
af3ea37176
[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-19 22:05:42 +08:00
Guoming Zhang
1240724da2
[None][doc] Replace the main in the examples' link with commit id. (#7837)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-18 23:44:00 +08:00
Yan Chunwei
2f3e3ae465
[https://nvbugs/5516710][fix] fix Llama 3.3 TP PP case (#7717)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-18 03:35:16 +08:00
Tao Li @ NVIDIA
015e149211
[https://nvbugs/1234567][fix] Revert https://github.com/NVIDIA/TensorRT-LLM/pull/7768/files (#7813)
Signed-off-by: Tao Li
2025-09-18 03:34:05 +08:00
Guoming Zhang
22c120e27b
[None][doc] Update docker cmd in quick start guide and trtllm-serve … (#7787)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-17 20:35:05 +08:00
Yuxian Qiu
a838c2cb10
[https://nvbugs/5522332][fix] Pin numpy version for Gemma. (#7783)
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
2025-09-17 16:23:27 +08:00
Guoming Zhang
de66d37754
[TRTLLM-7958][doc] add 1.0 release notes (#7605)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
Co-authored-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
2025-09-17 14:38:18 +08:00
Yukun He
88fe78e0af
[https://nvbugs/5517023][fix] Pass allreduce strategy and force NCCL on pre-Blackwell arch (#7768)
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
2025-09-17 13:28:43 +08:00
Guoming Zhang
2d7af4b32c
[https://nvbugs/5468897][fix] fix invalid expression for disabling pa… (#7762)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-17 11:14:54 +08:00
Yan Chunwei
b940ebf4e3
[None][doc] Enhance api reference doc by labeling stable APIs (#7751)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-17 10:20:26 +08:00
Wanli Jiang
14aa34fe54
[https://nvbugs/5509024][fix] Print full parsed outputs and update keywords for multimodal model (#7670)
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
2025-09-16 17:44:54 +08:00
Guoming Zhang
64f7cca5fa
[https://nvbugs/5519525][fix] fix doc invalid link for bug 5519525 (#7753)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-16 16:27:04 +08:00
Shi Xiaowei
7cf1d5a518
[None][doc] Fix the link in the doc (#7754)
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
2025-09-16 15:49:44 +08:00
Yi Zhang
7df515e335
[https://nvbugs/5355219][fix] Fix trtllm moe backend test config and Qwen3 MoE multi node (#7724)
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
2025-09-16 10:33:35 +08:00
Ivy Zhang
aaa381d169
[https://nvbugs/5512734][fix] Update kv cache config for maverick (#7710)
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
2025-09-15 22:53:30 +08:00
bhsueh_NV
2d40adb874
[https://nvbugs/5437405][fix] cherry-pick PR 7000 (qwen3 235b eagle3 ci) (#7702)
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
2025-09-15 16:03:36 +08:00
Guoming Zhang
9d719dd6d2
[None][doc] Add labels description note into llm api section (#7696)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-15 14:15:09 +08:00
Yanchao Lu
41a341a1dc
[None][ci] Test waives for the release/1.0 branch 09/15 (#7700)
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
2025-09-15 09:24:04 +08:00
Yilin Fan
e5ba99c6de
[https://nvbugs/5398180][feat] Improve Llama4 performance for small max_seqlen cases (#7681)
Signed-off-by: Yilin Fan <206948969+nv-yilinf@users.noreply.github.com>
2025-09-15 09:04:32 +08:00
brb-nv
c0e4fce03f
[https://nvbugs/5501557][fix] Fix out-of-bounds vector access for model with multiple layer types (#7636)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-09-10 20:34:25 -07:00
Guoming Zhang
541fd3ecb8
[https://nvbugs/5474409][fix] Disable concurrent loading by default (#7663)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-11 00:11:17 +08:00
Leslie Fang
9ca8662b26
[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 (#7673)
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
2025-09-10 23:16:25 +08:00
WeiHaocheng
68b7bad447
[https://nvbugs/5477730][fix] Fix the alltoall case when tp_size larg… (#7671)
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
2025-09-10 20:21:09 +08:00
Guoming Zhang
7c2f04ffec
[None][doc] Use hash id for external link (#7641)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-09 04:34:05 -04:00
Guoming Zhang
49dcc0df53
[None][doc] Fix a invalid link and a typo. (#7634)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-09 00:49:28 -04:00
Simeng Liu
f4736aec8e
[https://nvbugs/5470782][chore] Remove the skip statement in 1.0 rele… (#7573)
Signed-off-by: Simeng Liu <simengl@nvidia.com>
2025-09-08 21:04:14 -07:00
Liao Lanyu
af3f03cbff
[https://nvbugs/5455140][fix] unwaive release/1.0 DS R1 test cases with bug already fixed (#7432)
Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
Co-authored-by: Lanyu Liao <lancelly@users.noreply.github.com>
2025-09-09 09:48:59 +08:00
peaceh-nv
7784b3327f
[https://nvbugs/5503423][waive] Waive Llama3.1-70B-FP8 test on RTX PRO 6000 (#7603)
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
2025-09-09 09:29:07 +08:00
HuiGao-NV
5206f1ce47
[https://nvbugs/5474169][fix] seq_len mismatch between kv cache manager and graph attn metadata (#7606)
Signed-off-by: Hui Gao <huig@nvidia.com>
2025-09-09 08:32:31 +08:00
Guoming Zhang
f6365e654f
[None][doc] Fix a invalid link. (#7617)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-08 20:33:35 +08:00
Yan Chunwei
12041338a4
[https://nvbugs/5416501][doc] add known issues to llmapi doc (#7560)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: Ryan McCormick <mccormick.codes@gmail.com>
2025-09-08 04:42:54 -04:00
Yiteng Niu
88d1bde4d3 [None][infra] update nspect version (#7552)
Signed-off-by: Yiteng Niu <6831097+niukuo@users.noreply.github.com>
2025-09-06 18:16:55 +08:00
Yanchao Lu
2cb5b9f31b [None][ci] Increase the number of retries in docker image generation (#7557)
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
2025-09-06 18:16:36 +08:00
Yanchao Lu
275a09d0a2 Revert "[https://nvbugs/5461761][fix] Remove the waiver (#7427)"
This reverts commit 4612906b67.
2025-09-06 18:11:34 +08:00
Guoming Zhang
01c4ece911
[None][doc] Rename TensorRT-LLM to TensorRT LLM. (#7554)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-05 16:54:57 +08:00
Guoming Zhang
f9187b2fda
[None][doc] Update kvcache part (#7549)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-05 03:46:13 -04:00
Yukun He
e07fa9ddc5
[https://nvbugs/5496960][fix] Fix Gemma model forward. (#7509)
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
2025-09-04 19:09:43 +08:00
Guoming Zhang
cabda243f1
[TRTLLM-5930][doc] 1.0 Documentation. (#6696)
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-09-04 05:29:43 -04:00
Ziyi Xiong
4612906b67
[https://nvbugs/5461761][fix] Remove the waiver (#7427)
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
2025-09-04 11:34:25 +08:00
Yan Chunwei
ad80819ef0
[https://nvbugs/5351244][fix] test_mpi_session (#7501)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-09-04 10:10:43 +08:00
dongxuy04
9eecdf2ee9
[TRTLLM-7008][fix] cherrypick fix to 1.0 Add automatic shared memory delete if already exist (#7433)
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
2025-09-02 11:23:53 +08:00