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
3,128 Commits 25 Branches 59 Tags 2.1 GiB
f1d02b5664
Commit Graph

3128 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
peaceh-nv
f1d02b5664
[https://nvbugs/5570575][fix] : Use less kv cache memory on SM120 (#9054) 
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
 2025-11-11 15:42:08 +08:00
Vincent Zhang
08f8f96cbd
[https://nvbugs/5284463][fix] fix ada fp8 group gemm lacks shared memory (#9044) 
Signed-off-by: Vincent Zhang <vinczhang@nvidia.com>
 2025-11-11 13:00:47 +08:00
Lizhi Zhou
0649b77d16
[https://nvbugs/5608743][chore] unwaive test (#8994) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-11-10 05:59:29 -08:00
Zhanrui Sun
7ff0b13de3
[TRTLLM-9080][infra] upgrade tritonserver DLFW 25.10 (#8877) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-11-09 22:36:56 -08:00
Guoming Zhang
5192af14ea
[TRTLLM-9073][doc] Add the missing content for model support section and fix… (#9033) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-11-10 13:44:16 +08:00
Yiqing Yan
572f9be06f
[None][chore] Lock onnx version <1.20.0 and remove WAR for TRT 10.13 (#9007) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-10 12:50:37 +08:00
Emma Qiao
a74ce266d3
[None][infra] Waive failed tests for release branch 11/07 (#9026) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-09 18:18:49 +08:00
dominicshanshan
def2ad5107
[https://nvbugs/5575920][fix] Fix cublas/cublasLt handle creation memory not sufficient error (#8900) 
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-11-07 10:14:00 -08:00
Guoming Zhang
70e4d97c37
[None][doc] Replace the relative links with absolute links in README.md. (#8997) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-11-08 00:27:12 +08:00
Zhanrui Sun
fcfe6f86f9
[TRTLLM-9213][infra] Fix boost issue (#9005) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-11-07 02:08:44 -08:00
Ivy Zhang
5cf3f0c981
[https://nvbugs/5636946][fix] Update test model (#8993) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2025-11-07 15:13:29 +08:00
Emma Qiao
ede230cb3a
[None][infra] Waive failed tests for release branch 11/06 (#8966) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-07 09:01:26 +08:00
Lucas Liebenwein
991e507e11
[https://nvbugs/5642736][fix] fix AutoDeploy pattern matcher for torch 2.9 (#8920) (#8958) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Co-authored-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-06 10:21:32 -08:00
Shiyu Li
519eda29bd
[https://nvbugs/5597647][fix] Fix MNNVL unit test failed due to accuracy issue on Hopper (#8891) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
Signed-off-by: Shiyu Li <timlee0212@outlook.com>
 2025-11-06 18:28:06 +01:00
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