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
1,497 Commits 25 Branches 59 Tags 2.1 GiB
cbcc55e073
Commit Graph

1497 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
ruodil
cbcc55e073
test: remove duplicate cases in perf sanity test (#5870) 
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
 2025-07-09 15:36:22 +10:00
Yi Zhang
39ad6023b7
doc: Update gb200 doc (#5840) 
Signed-off-by: yizhan <187001205+yizhang-nv@users.noreply.github.com>
 2025-07-08 20:22:06 +09:00
Bo Li
6d7a2cb1c5
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>
 2025-07-08 18:12:48 +08:00
QI JUN
f8b4077654
[nvbugs/5326453] Avoid nesting NCCL grouping in allgather OP (#5789) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-08 15:39:27 +09:00
Bo Li
6062dc675f
fix: [https://nvbugspro.nvidia.com/bug/5345215] Unwaive for bug 5345215. (#5606) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-07-08 13:11:08 +09:00
Perkz Zheng
5a50e2b26b
[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>
 2025-07-08 10:35:38 +08:00
Yan Chunwei
97f4c9e24f
[nvbug5266240] chore: unwaive test_llm_with_dummy_weights (#5744) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-07-07 22:13:34 +08:00
Pengyun Lin
0a0ac7b5dc
[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>
 2025-07-07 19:26:13 +08:00
QI JUN
d47ac4e3e5
cherry pick #5416 (#5776) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-07 17:19:38 +08:00
QI JUN
4fa9284612
[nvbug/5302638][nvbugs/5310314] fix _handle_cancelled_requests (#5532) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-07 16:51:24 +08:00
Martin Marciniszyn Mehringer
06f83277b2
Fix docker cache mount (#5763) 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
 2025-07-07 00:18:55 -07:00
QI JUN
3a58db88c8
fix _pad_attention_dp_dummy_request (#5583) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-07 14:13:54 +08:00
Pengyun Lin
7524c77e1e
[nvbug 5004744][fix] rewrite completion API to avoid repetitive tokens (#5201) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-07-07 15:06:49 +09:00
brb-nv
9106b5d9a5
fix: Skip rope scaling for local layers in Gemma3 VLM (#5773) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-07 13:36:23 +08:00
ruodil
6103466de2
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>
 2025-07-07 13:11:41 +10:00
Yanchao Lu
aa4d0f04eb
[Infra] - Always use x86 image for the Jenkins agent (#5756) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-07-06 10:25:20 +08:00
Iman Tabrizian
518915b5c6
[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>
 2025-07-04 12:52:35 -04:00
Yi Zhang
5ac92bb8ff
[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>
 2025-07-04 23:23:41 +09:00
Yiqing Yan
3e44db11c9
[Infra][nvbugs/5370968] - Unwaive l0 test (#5750) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-07-04 15:27:53 +08:00
Yukun He
b0354ef43c
[5321981] fix: Fix the Llama3.1 405B hanging issue. (#5698) 
Correct the output shape of the fusedLayerNormPlugin.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-07-04 12:29:19 +08:00
Yi Zhang
53394e0030
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>
 2025-07-04 13:26:53 +09:00
brb-nv
2b66fe8fbd
[nvbug/5341178][fix] Fix OOM in Llama 4 accuracy test (#5735) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-04 10:55:34 +08:00
Dom Brown
2aacdba1e4
[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>
 2025-07-04 10:38:08 +08:00
Faraz
8a8d2e9901
[NVBUG:5355009] Modify check for fuse_fp4_quant on SM120 (#5651) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
 2025-07-03 22:08:15 +09:00
Linda
14f938e510
Doc: Update invalid hugging face URLs (#5683) 
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
 2025-07-03 09:37:01 +02:00
Emma Qiao
2f9d0619c3
[Infra] - Waive failed cases on release/0.21 (#5674) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-07-02 22:23:54 -04:00
brb-nv
a3c0cf02ce
fix: Investigate Gemma3 1B decoder output discrepancy (#5564) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-03 09:55:25 +08:00
Frank
92d3a2d0e0
[https://nvbugspro.nvidia.com/bug/5351333][fix] Update to chunking calculation. (#5625) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-07-02 17:48:02 +08:00
bhsueh_NV
d5606b062a
fix: [https://nvbugs/5355219] Fix bug of Qwen3 235B CI on dgx_gb200 (#5602) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-07-02 10:07:01 +08:00
Kaiyu Xie
682b164b9b
doc: Fix outdated config in DeepSeek best perf practice doc (#5638) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-07-01 04:58:50 -04:00
Yi Zhang
aa0b9278d2
test: add more tests for GB200 with 8 GPUs/2 nodes in L0 tests (#5397) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2025-07-01 01:06:47 -04:00
Zheng Duan
1824c44004
[nvbug 5300551] test: increase block count in eviction test (#5465) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-07-01 10:48:25 +08:00
nv-guomingz
9fe1dd6be1
fix:https://nvbugs/5362398 (#5609) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-06-30 13:29:40 -04:00
Yan Chunwei
d6c81bad97
fix [nvbug5351244]: test_mpi_session submit sync/async (#5608) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-07-01 00:48:59 +08:00
Emma Qiao
647e070ed6
[Infra][release/0.21]Update nccl to 2.27.5 (#5539) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-06-29 20:50:15 +08:00
Venky
4fc0666daa
[cherry-pick] [CI] Waive test_fp8_block_scales_4gpus[ep4-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] (#5553) 
Signed-off-by: Venky <23023424+venkywonka@users.noreply.github.com>
 2025-06-28 01:15:04 +08:00
ixlmar
abb7357f25
[TRTLLM-5989, TRTLLM-5991, TRTLLM-5993] doc: Update container instructions (#5490) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-06-27 07:09:41 -07:00
Yan Chunwei
b78ad754c8
ci: unwaive llmapi launch test (#5281) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-06-27 14:10:45 +08:00
Emma Qiao
e2054bb2aa
[Infra][release/0.21] - waive failed tests (#5537) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-06-27 13:58:13 +08:00
ixlmar
312fd47f84
fix: constrain grepping in docker/Makefile (#5493) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-06-26 13:44:40 +02:00
Kaiyu Xie
30a2a8b81c
doc: Fix benchmark cmd in disagg scripts (#5516) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-06-26 17:23:24 +08:00
ixlmar
a811077f90
fix: fix regression in LOCAL_USER (#5517) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-06-26 11:10:55 +02:00
Anurag Mukkara
c2799d0465
[nvbug/5354825] Fix nougat test image url (#5496) 
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
 2025-06-26 10:10:18 +08:00
Yan Chunwei
87ead4ecbe
[nvbug 5273941] fix: broken cyclic reference detect (#5417) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-06-26 07:35:35 +08:00
Martin Marciniszyn Mehringer
fc64f139e4
Fix permission for local user issues in NGC docker container. (#5373) 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
 2025-06-25 14:10:20 +02:00
Emma Qiao
b6d23d58c4
[Infra] - Waive failed tests on release/0.21 (#5477) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-06-25 19:01:55 +08:00
HuiGao-NV
5cd87bee41
tests: Set kv cache free memory fraction in test case (#5462) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-06-25 16:27:46 +08:00
ruodil
5e50fcc51b
test: set enable_attention_dp=True in default deepseek settings (#5461) 
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
 2025-06-25 14:21:14 +08:00
Wanli Jiang
af5839303d
feat: TRTLLM-5941 Upgrade xgrammar to 0.1.18 (#5364) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-06-25 14:10:50 +08:00
brb-nv
32f50ded17
nvbugs-5331031; nvbugs-5344203 - address intermittent issues with Mistral Small multimodal for BS=8 (#5453) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-06-25 11:45:14 +08:00