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
3,114 Commits 25 Branches 59 Tags 2.1 GiB
1ef38f24f4
Commit Graph

3114 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jin Li
1ef38f24f4
[https://nvbugs/5570599][fix] Set KVCache free_gpu_memory_fraction fo… (#8780) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-11-06 05:58:07 -08:00
shuyixiong
69dec201bd
[https://nvbugs/5630700][chore] Unwaive Qwen3_235B_A22B test (#8901) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-11-06 15:32:39 +08:00
Jin Li
f040ef9ffd
[https://nvbugs/5467531][fix] Fix moe test and wide ep fake impl (#8883) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-11-06 11:40:50 +08:00
sunnyqgg
c2fe686e3e
[https://nvbugs/5608930][fix] Wavie TestQwen3_8B::test_chunked_prefill for bug 5608930 (#8940) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-11-05 01:52:09 -08:00
Emma Qiao
6db74e8a0a
[TRTLLM-8813][infra] Reduce GB200 multi-node test stages for release (#8860) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-04 23:29:28 -08:00
Guoming Zhang
b941d7acbb
[https://nvbugs/5634220][fix] Add developer guide back and fix some i… (#8911) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-11-05 10:17:01 +08:00
Bo Deng
43843778a7
[https://nvbugs/5601682][fix] unwaive test_disaggregated_deepseek_v3_… (#8888) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
 2025-11-05 09:33:57 +08:00
Simeng Liu
0206d8d0fc
[https://nvbugs/5606136][fix] Fix torch.onnx.export with pytorch upgrade to fallback to dynamo=False. (#8917) 
Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2025-11-04 14:11:48 -08:00
JunyiXu-nv
c329f5f78b
[https://nvbugs/5569754][chore] Adjust max batch size to prevent OOM (#8876) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-11-04 18:34:26 +01:00
Yan Chunwei
cacb8a84f2
[https://nvbugs/5606266][test] move qwen3 multi-node test to the qa list (#8908) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-11-04 02:12:02 -08:00
Shi Xiaowei
324f63f26a
[https://nvbugs/5451272][fix] unwaive the test (#8608) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-11-04 01:31:41 -08:00
xiweny
7d8a913406
[https://nvbugs/5596343] [test] Update accuracy baseline for GPT-OSS-20B (#8842) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
Signed-off-by: dongfengy <99041270+dongfengy@users.noreply.github.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
 2025-11-04 16:04:11 +08:00
Ivy Zhang
baa6ba0d69
[None][chore] Update test list (#8835) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2025-11-03 21:42:01 -08:00
brb-nv
095b7a3ad5
[https://nvbugs/5521253][fix] Enable Gemma3 12B & 27B on SM100 (#8666) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-11-03 14:49:36 -08:00
Emma Qiao
9f1d274a26
[None][infra] Waive failed tests for release branch on 11/03 (#8879) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-03 02:59:33 -08:00
Zhanrui Sun
e9e1a3668e
[None][infra] Modify wheel path from cuda13/ to dlfw/ (#8868) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-11-03 00:55:42 -08:00
sunnyqgg
ccadb66efe
[https://nvbugs/5461796][fix] Unwaive test test_llmapi_speculative_decoding_mtp (#8832) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-11-03 16:53:24 +08:00
sunnyqgg
d82197846d
[https://nvbugs/5608930][fix] Unwaive test 5608930 (#8831) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-11-03 15:09:58 +08:00
yunruis
07077fb070
[https://nvbugs/5606268][fix] Fix program exit segment fault triggered CublasMMWarpper deconstructor (#8834) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
 2025-11-03 14:46:01 +08:00
Yan Chunwei
0d105448b1
[https://nvbugs/5606266][fix] unwaive test (#8867) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-11-02 21:43:58 -08:00
Zhanrui Sun
776bb25bfd
[TRTLLM-8658][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0 (#8621) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-03 09:24:58 +08:00
dongxuy04
d81ebb5b4d
[https://nvbugs/5444687][fix] Cherrypick online EPLB CI fix from main to release 1.1 (#8854) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-11-03 09:17:51 +08:00
dongfengy
f5575a9146
[https://nvbugs/5474119][fix] Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/8809 (#8847) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2025-11-02 16:44:06 -08:00
Yanchao Lu
5ff1adbda8
[None][fix] WAR for tensorrt depending on the archived nvidia-cuda-runtime-cu13 package (#8858) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-02 09:21:01 +08:00
Barry Kang
f22a87f296
[https://nvbugs/5325296][fix] Enable relaxed acceptance test on Blackwell (#8709) 
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-10-31 15:02:06 -07:00
Lucas Liebenwein
752cc3a8cb
[https://nvbugs/5606166][fix] AutoDeploy: use tuples for cudagraph shape lookup (#8772) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-31 13:59:48 +01:00
Zhanrui Sun
d2071d7ed7
[None][infra] Remove invaild waived tests which not in release branch (#8841) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-10-31 03:02:34 -07:00
Emma Qiao
421d48f402
[None][infra] Skip failed tests for release branch (#8833) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-10-31 15:04:54 +08:00
Yukun He
a1d912688c
[https://nvbugs/5623960][fix] Compress the warning log of AutoTuner when encountering tactic failures. (#8795) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-10-31 12:55:56 +08:00
Jin Li
28673f3e9c
[https://nvbugs/5488118][fix] Unwaive passed tests (#8758) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-10-31 10:46:44 +08:00
Emma Qiao
9ee0075921
[TRTLLM-8971][infra] Cherry-pick for Update gpu key for B300/GB300 (#8724) (#8796) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-10-30 06:12:16 -07:00
Dom Brown
9410ce3bea
[https://nvbugs/5575841] [test] Move test_moe.py to serial tests to improve stability + unwaive FP4 MoE torch unit tests (#8422) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-10-30 13:57:56 +01:00
Jin Li
0dac57f2bc
[https://nvbugs/5569534][fix] Warm up with different sizes for more s… (#8515) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-10-29 22:29:06 -07:00
Enwei Zhu
c1bac95382
[https://nvbugs/5422621][fix] fix EPLB init hang (cherry-pick #8649) (#8727) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: dongxuy04 <78518666+dongxuy04@users.noreply.github.com>
 2025-10-30 10:31:34 +08:00
Emma Qiao
ec510ad72a
[None][infra] Waive failed tests for release branch (#8760) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-10-29 06:32:30 -07:00
JunyiXu-nv
6adccd758d
[https://nvbugs/5606268][fix] Separate cuda graph workspace to prevent IMA (#8685) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-10-29 09:43:30 +01:00
sunnyqgg
e9aa8b222f
[https://nvbugs/5556020][fix] cherry-pick fix test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3 dimension mismatch (#8644) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-10-29 15:44:25 +08:00
Zhanrui Sun
beafc39764
[None][fix] add readme copy to wheel stage to avoid setup.py failure (cherry-pick #8736) (#8754) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Co-authored-by: Faraz <58580514+farazkh80@users.noreply.github.com>
 2025-10-29 00:27:37 -07:00
xiweny
f49f42db59
[https://nvbugs/5601203] [fix]Restrict fp8 blockscale moe case (#8583) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
 2025-10-29 10:47:32 +08:00
Chuang Zhu
b326be25e7
[https://nvbugs/5578175][fix] Fix block range index (#8470) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-10-28 11:42:23 -07:00
Pengyun Lin
b334102544
[https://nvbugs/5564465][fix] Overwrite only if default_max_tokens is legal (#8538) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-10-28 10:15:26 +01:00
Eran Geva
db3c373d3a
[https://nvbugs/5572320][fix] Ported test_ad_trtllm_bench.py from main (#8671) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-10-28 09:41:32 +02:00
Yukun He
e04354bc09
[https://nvbugs/5608489][fix] Fix output unpack issues for Llama3/4 NVFP4 models. (#8679) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-10-28 14:21:47 +08:00
Shiyu Li
28c9a51c06
[https://nvbugs/5597647][fix] Fix MNNVL Allreduce accuracy issue on Hopper (#8612) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-10-26 23:06:45 -07:00
Yanchao Lu
389cbd7611
[None][docs] Update Python wheel's short-/long-descriptions (#8485) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-10-27 08:36:29 +08:00
Emma Qiao
b05555faeb
[None][infra] Waive failed tests for release 10/24 (#8656) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
 2025-10-24 21:53:35 +08:00
Ivy Zhang
1859b55d22
[None][test] Clean cache for certain easily hang cases (#8619) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Larry Xu <197874197+LarryXFly@users.noreply.github.com>
 2025-10-24 08:17:32 -04:00
Jie Li
7749ec406b
[https://nvbugs/5587456][fix] Remove multimodal test cases using TRT backend (#8611) 
Signed-off-by: Jie Li <lijie@nvidia.com>
 2025-10-24 18:04:43 +08:00
Yiqing Yan
25ec125726
[None][chore] Disable GB300 stages in release branch due to nodes will be offline temporarily (#8645) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-10-24 05:21:14 -04:00
Jie Li
4b52054bdd
[https://nvbugs/5541145][fix] Remove DeepSeekR1 test case from H20 to prevent OOM (#8610) 
Signed-off-by: Jie Li <lijie@nvidia.com>
 2025-10-24 05:20:40 -04:00