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
1,819 Commits 25 Branches 59 Tags 2.1 GiB
01b2def5ef
Commit Graph

1819 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Zhanrui Sun
01b2def5ef
infra: [TRTLLM-6331] Support show all stage name list when stage name check failed (#5946) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-07-15 12:06:03 +09:00
jiahanc
24dfd4cd0b
Doc: Update llama-3.3-70B guide (#6028) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
 2025-07-15 11:37:26 +09:00
Daniel Stokes
dd2491f47d
fix: Fix MOE benchmark to rotate buffers to prevent L2 cache reuse (#4135) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-07-15 13:40:42 +12:00
Rashid Kaleem
2ea4077993
[Model load] Fix llama min-latency model load (#5883) 
Signed-off-by: Rashid Kaleem <4079439+arekay@users.noreply.github.com>
 2025-07-15 09:29:19 +08:00
Yechan Kim
2320f12321
doc: update EXAONE 4.0 news (#6034) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-07-15 10:26:51 +09:00
ixlmar
f225f5cd2e
[nvbugs-5318143] fix: restrict PyTorch memory usage to avoid OOMs (#5964) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-07-15 06:49:42 +08:00
Daniel Stokes
f277afdd93
perf: Enable 128x256 tile shapes for FP4 MOE CUTLASS backend (#5986) 
Signed-off-by: Daniel Stokes <40156487+djns99@users.noreply.github.com>
 2025-07-14 14:04:15 -07:00
Iman Tabrizian
c4ee535afb
[fix] fix eagle3 two model disaggregated serving test (#6014) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-07-15 04:26:04 +09:00
Robin Kobus
6d4b045d1f
refactor: Remove enforced sorted order of batch slots (#3502) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-14 17:23:02 +02:00
brb-nv
f5f5be9e94
enh: Bidirectional mask with multiple images for Gemma3 (#5976) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-14 22:39:18 +08:00
brb-nv
1a2d96919c
feat: Update Gemma3 Vision Encoder (#5973) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-14 22:38:10 +08:00
Alex Zhang
6c30d78b78
[TRTLLM-5653][infra] Run docs build only if PR contains only doc changes (#5184) 
Signed-off-by: Alex Zhang <13271672+zhanga5@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Alex Zhang <13271672+zhanga5@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-07-14 21:40:33 +08:00
Yechan Kim
63139fdcff
feat: EXAONE4.0 support (#5696) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-07-14 22:28:10 +09:00
Clay
dbf29184dc
fix #4974: A thread leak issue in scaffolding unittest (#5020) 
Signed-off-by: Clay <ccs96307@gmail.com>
 2025-07-14 20:22:03 +09:00
Kaiyu Xie
aa97fbb2ad
[Nvbug/5383670] fix: switch test case to non-fp4 ckpt for more GPU coverage (#5882) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-07-14 20:21:46 +09:00
Yiqing Yan
c720d7f779
Waive L0 test (#6002) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-07-14 19:55:34 +09:00
Zhanrui Sun
3a0ef73414
infra: [TRTLLM-6242] install cuda-toolkit to fix sanity check (#5709) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-07-14 18:52:13 +09:00
Zhenhuan Chen
30608a5e6d [https://nvbugs/5355316] fix: update torch.compile option to fix triton store_cubin error (#5865) 
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-07-14 17:17:30 +08:00
Robin Kobus
5a61d64b5b [nvbugs/5345391] fix: chunked prefill + overlap scheduling (#5761) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Pengyun Lin
3fcaa8a310 [nvbug 5327706][fix] fix mgmn postprocess error (#5835) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
ruodil
347520494b test: remove duplicate cases in perf sanity test (#5870) 
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Yi Zhang
966e41a900 doc: Update gb200 doc (#5840) 
Signed-off-by: yizhan <187001205+yizhang-nv@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Bo Li
6d79559f3e fix: [https://nvbugs/5351130][https://nvbugs/5333654] Unwaive for bug 5351130 and 5333654. (#5821) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Bo Li
2991cf4b80 fix: [https://nvbugspro.nvidia.com/bug/5345215] Unwaive for bug 5345215. (#5606) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Perkz Zheng
4a0b7a0cf1 [https://nvbugspro.nvidia.com/bug/5355054] fallback to cubins for fp8 fmha kernels on Ada. (#5779) 
Signed-off-by: Qidi Sang <200703406+qsang-nv@users.noreply.github.com>
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Co-authored-by: qsang-nv <200703406+qsang-nv@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Yan Chunwei
3e1fd983c3 [nvbug5266240] chore: unwaive test_llm_with_dummy_weights (#5744) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Pengyun Lin
388b4919b8 [nvbug 5304752][fix] enhance _check_arguments to filter illegal requests for pytorch backend (#5541) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Martin Marciniszyn Mehringer
c321fb8f81 Fix docker cache mount (#5763) 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Pengyun Lin
6992616c1f [nvbug 5004744][fix] rewrite completion API to avoid repetitive tokens (#5201) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
ruodil
278a1a7df3 test: fix some test failure and add llama_nemotron models in perf sanity test, add more torch cases (#5693) 
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Iman Tabrizian
c8874a7f94 [nvbug/5337601][fix] Fix disagg + speculative decoding (#5558) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Co-authored-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Yi Zhang
9cc4e5d50e [nvbugs/5336321][fix] Enable attention dp = False test case, Fix TRTLLM Gen Moe workspace allocation (#5463) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: yizhan <187001205+yizhang-nv@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Yi Zhang
e5e87ecf34 test: Move some of the test from post merge to pre-merge, update dgx b200 test case (#5640) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
brb-nv
869e88304a [nvbug/5341178][fix] Fix OOM in Llama 4 accuracy test (#5735) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
Dom Brown
afaa388bee [TRTLLM-6100] fix: Nvbug 5356427: autotuned TRTLLM Gen fp8 block scale MoE illegal memory access (#5676) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-07-14 17:17:30 +08:00
WeiHaocheng
4d8920982a
fix: set allreduce strategy to model config (#5955) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-07-14 17:59:11 +09:00
dominicshanshan
c9e7f831dc
Breaking change: perf: [TRTLLM-4662] Enable cuda graph by default (#5480) 
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-07-14 16:42:23 +08:00
dongxuy04
c04570a506
Use huge page mapping for host accessible memory on GB200 (#5963) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-07-14 16:11:04 +08:00
Yan Chunwei
9c673e9707
[TRTLLM-6160] chore: add sampling examples for pytorch (#5951) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-07-14 15:28:32 +09:00
Enwei Zhu
ed77ef2ff4
fix: Fix MoE benchmark (#5966) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-07-14 15:17:26 +09:00
Yan Chunwei
c30eead09f
[TRTLLM-6164][TRTLLM-6165] chore: add runtime example for pytorch (#5956) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-07-14 14:09:39 +08:00
wili
cfcb97af0e
[BUG5388075][fix] Fix error in post-merge-tests (#5949) 
Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
 2025-07-14 14:33:39 +09:00
Xianjie Qiao
c7ffadf692
Fix errors in wide-ep scripts (#5992) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2025-07-14 14:07:27 +09:00
QI JUN
ce39409530
fix cancel request logic (#5800) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-14 10:23:20 +08:00
Yuan Tong
a36ac45c4d
fix: fast redux detection in trtllm gen routing kernel (#5941) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-07-13 16:35:07 +08:00
wili
3dfc819849
[BUG5374319][fix] WAR for draft-target-model unit tests error (#5958) 
Signed-off-by: wili-65535 <wili-65535@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-07-12 23:48:57 +09:00
Mike Iovine
8950223f6f
[fix] Remove SpecConfig and fix thread leak issues (#5931) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-07-12 21:03:24 +09:00
Enwei Zhu
bc1d4fb5da
[NvBug 5378370] fix: Fix alltoall for llama4 (apply_router_weight_on_input=True) (#5902) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-07-12 15:50:31 +09:00
Chang Liu
308776442a
[nvbug/5308432] fix: extend triton exit time for test_llava (#5971) 
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-07-12 12:56:37 +09:00
juney-nvidia
63cf929188
Added code owners for LLM API (#5960) 
Signed-off-by: Jun Yang <143764042+juney-nvidia@users.noreply.github.com>
 2025-07-12 10:30:17 +09:00