Commit Graph

2262 Commits

Author SHA1 Message Date
Yan Chunwei
85406f9dda
[https://nvbugs/5720482][fix] Fix test rpc streaming (#9902)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-12-13 01:14:43 -08:00
shuyixiong
8cbf2d958c
[TRTLLM-9738][chore] Guard accuracy with nccl allreduce strategy (#9793)
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
2025-12-13 01:02:11 -08:00
Balaram Buddharaju
6a6e41f802
[TRTLLM-9468][chore] Update disagg benchmarking scripts to support context parallelism (#9720)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-12-12 22:29:41 -08:00
bhsueh_NV
e49c70f6df
[None][feat] Support Mistral Large3 LLM part (#9820)
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
2025-12-13 11:44:27 +08:00
Balaram Buddharaju
461446045e
[TRTLLM-9493][feat] Add helixPostProcessNative kernel for cp_dim=2 (#9924)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-12-12 16:49:25 -08:00
tburt-nv
6147452158
[https://nvbugs/4141427][chore] Add more details to LICENSE file (#9881)
Signed-off-by: Tyler Burt <195370667+tburt-nv@users.noreply.github.com>
2025-12-13 08:35:31 +08:00
Chuang Zhu
4cc4cbe926
[https://nvbugs/5716787][fix] terminate nixl running when exiting (#9785)
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Co-authored-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-12-12 11:15:02 -05:00
Chuang Zhu
9c59c9f920
[https://nvbugs/5643787][fix] remove the war path for notify to itself (#9834)
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
2025-12-12 11:10:05 -05:00
JunyiXu-nv
2fec53dfa5
[TRTLLM-9637][feat] Support tool parser for Kimi K2 (#9830)
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
2025-12-12 23:32:39 +08:00
Yihan Wang
9df4dad3b6
[None][fix] Introduce inline namespace to avoid symbol collision (#9541)
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
2025-12-12 23:32:15 +08:00
Balaram Buddharaju
af315d8ef1
[TRTLLM-5972][chore] Load balance decode token KV cache with helix parallelism (#9757)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-12-12 22:29:05 +08:00
Lucas Liebenwein
e767fc649a
[None][feat] AutoDeploy: prepare_metadata revisited (#9764)
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
2025-12-12 20:14:14 +08:00
ruodil
9b3e5e90ee
[None][test] fix a typo in model name in script (#9867)
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
2025-12-12 17:35:55 +08:00
chenfeiz0326
61745f034a
[https://nvbugs/5727481][ci] Fix Port Conflict in Perf-Sanity CI Test (#9896)
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
2025-12-12 17:16:50 +08:00
kris1025
2fc94e5dd7
[None][chore] unwaive qwen3 accuracy test (#9895)
Signed-off-by: linquanh <linquanh@nvidia.com>
2025-12-12 16:30:09 +08:00
Yihan Wang
711016c799
[https://nvbugs/5736923][infra] Waive timeout disaggregated/test_auto_scaling[http-round_robin] test (#9942)
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
2025-12-12 15:15:13 +08:00
Ivy Zhang
fded6c393d
[TRTLLM-9262][test] add groupgemm ada case for rcca (#9833)
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
2025-12-12 13:23:33 +08:00
dominicshanshan
093465ed29
[https://nvbugs/5599176][fix] Unwaive fixed test for Ray (#9861)
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
2025-12-12 11:24:05 +08:00
xinhe-nv
e8efeb765d
[TRTLLM-9717][fix] fix multi nodes tests cases (#9736)
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
2025-12-12 10:14:23 +08:00
Venky
fd1270b9ab
[TRTC-43] [feat] Add config db and docs (#9420)
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
2025-12-12 04:00:03 +08:00
Simeng Liu
24f92721f2
[https://nvbugs/5597647][ci] Unwaive fixed tests. (#9812)
Signed-off-by: SimengLiu-nv <simengl@nvidia.com>
2025-12-12 02:29:30 +08:00
Erin
89dabf5aa1
[TRTLLM-9736][feat] AsyncLLM and verl integ (#9353)
Signed-off-by: Liwei Ma <liweim@nvidia.com>
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-authored-by: Liwei Ma <liweim@nvidia.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Co-authored-by: Superjomn <328693+Superjomn@users.noreply.github.com>
2025-12-11 09:33:25 -08:00
JadoTu
02edb19f43
[None] [feat] add eos_token_id in generation_config to sampling params (#9514)
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
2025-12-12 00:52:03 +08:00
xxi
488d38f88d
[TRTLLM-8959][feat] ConfigurableMoE support CUTLASS (#9772) 2025-12-12 00:22:13 +08:00
Yan Chunwei
04a39a4e2b
[None][chore] enable test_ipc.py (#9865)
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
2025-12-11 17:47:14 +08:00
Zongfei Jing
c76b428e2e
[TRTLLM-9685] [feat] Add gather fc1 kernel by cuteDSL (#9618)
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
2025-12-11 16:21:32 +08:00
JunyiXu-nv
454e7e59e5
[https://nvbugs/5718004][fix] Add warmup for cancellation test (#9860)
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
2025-12-11 12:20:33 +08:00
Bo Deng
c1d53ee43d
[https://nvbugs/5582258][fix] unwaive (#9650)
Signed-off-by: Bo Deng <deemod@nvidia.com>
2025-12-10 19:18:30 -08:00
fredricz-20070104
341cb1a12c
[None][chore] Add GB300 support since it does not support segment (#9731)
Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
2025-12-10 18:36:55 -08:00
Patrice Castonguay
2c0293c612
[https://nvbugs/5601682][fix] Unwaiving disagg test (#9627)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-12-10 13:42:26 -05:00
cheshirekow
2f030312a8
[TRTLLM-9228][infra] Verify thirdparty C++ process (#9367)
Signed-off-by: Josh Bialkowski <1309820+cheshirekow@users.noreply.github.com>
Co-authored-by: Josh Bialkowski <1309820+cheshirekow@users.noreply.github.com>
2025-12-10 21:01:19 +08:00
Yukun He
072f236002
[None][fix] Fully resolve the tactic recovery issues in AutoTuner serialized cache (#9835)
Restrict tactic types to those compatible with AutoTuner cache serialization and deserialization.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
2025-12-10 20:41:04 +08:00
dominicshanshan
0e78a4b244
[https://nvbugs/5702791][fix] Unwaive fixed test (#9844)
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
2025-12-10 14:01:44 +08:00
QI JUN
2c46126a93
[TRTLLM-9794][ci] move some deepseek test cases to gb200 (#9841)
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
2025-12-09 19:54:51 -08:00
zhanghaotong
36c9e7cfe6
[None][chore] Add unittest for otlp tracing (#8716)
Signed-off-by: zhanghaotong <zhanghaotong.zht@antgroup.com>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
2025-12-09 18:34:08 -08:00
dhansen-nvidia
2d33ae94d5
[https://nvbugs/5508301][feat] Move D->H copies to a worker thread whe… (#8463)
Signed-off-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
Signed-off-by: dhansen-nvidia <218031328+dhansen-nvidia@users.noreply.github.com>
Co-authored-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
2025-12-09 18:51:31 -05:00
Patrice Castonguay
414448bb37
[https://nvbugs/5719561][chore] Unwaive tests for nvbug 5719561 (#9801)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-12-09 18:21:50 -05:00
Patrice Castonguay
ff0ef19ee9
[https://nvbugs/5688388][chore] Unwaiving fixed disagg test (#9800)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-12-09 16:51:46 -05:00
Patrice Castonguay
7d7d05d8db
[None][chore] Adding flaky auto scaling test to waives (#9851)
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
2025-12-09 15:05:19 -05:00
Mike Iovine
07c76a5fac
[None][feat] Make 2-model spec dec use the 1-model kernels (Hopper) (#8810)
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
2025-12-09 11:06:31 -05:00
Dom Brown
3156f2e852
[https://nvbugs/5575841] [fix] Nvbug 5575841: Remove additional test waivers for TestMoEFP4 (#9788)
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
2025-12-09 13:37:55 +00:00
Emma Qiao
75bc386b65
[None][infra] Waive failed cases for main branch on 12/09 (#9839)
Signed-off-by: qqiao <qqiao@nvidia.com>
2025-12-09 19:39:29 +08:00
QI JUN
58c29957d9
[TRTLLM-9794][ci] move qwen3-next test cases to gb200 (#9827)
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
2025-12-09 01:58:25 -08:00
Stefan Niebler
d600b9f851
[TRTLLM-6756][feat] Update BeamSearch for TorchSampler (#9660)
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
2025-12-09 10:44:01 +01:00
Robin Kobus
76f49c903b
[None][fix] Additional model outputs for pipeline parallelism (#9794)
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-12-09 10:41:22 +01:00
yufeiwu-nv
fbcf03040f
[None][test] Refactor qa/llm_perf_nim.yml test list (#9700)
Signed-off-by: yufeiwu <230315618+yufeiwu-nv@users.noreply.github.com>
2025-12-08 22:00:43 -08:00
QI JUN
252769c930
[TRTLLM-9794][ci] remove duplicated test cases in DGX B200 (#9817)
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
2025-12-08 21:51:30 -08:00
Shi Xiaowei
b050804b63
[TRTLLM-6537][infra] extend multi-gpu tests related file list (#9614)
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
2025-12-09 12:54:53 +08:00
JunyiXu-nv
90890785eb
[https://nvbugs/5722653][fix] Fix config file used by disagg_client (#9783)
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
Signed-off-by: JunyiXu-nv <219237550+JunyiXu-nv@users.noreply.github.com>
2025-12-08 20:34:55 -08:00
Balaram Buddharaju
bafb60c1bc
[None][chore] Fix tests failing on pre-merge 12/08 (#9819)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-12-08 20:08:52 -08:00