kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-11 13:33:40 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,695 Commits 28 Branches 67 Tags 2 GiB
7bf4dd9f63
Commit Graph

2596 Commits

Author SHA1 Message Date
yufeiwu-nv
b130d58c88
[None][test] Remove most TRT-backend test cases in llm_perf_nim.yml (#10487) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-07 17:18:43 +08:00
xinhe-nv
872210468b
[TRTLLM-8638][fix] Add failed cases into waives.txt (#10474) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-07 03:23:43 -05:00
yingguo-trt
cbf8357e5f
[https://nvbugs/5726086][fix] update kimi-k2-1k1k dataset (#10473) 
Signed-off-by: yingguo-trt <244492186+yingguo-trt@users.noreply.github.com>
 2026-01-07 01:24:08 -05:00
xinhe-nv
be5579633e
[TRTLLM-8638][fix] Add failed cases into waives.txt (#10457) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-07 00:57:03 -05:00
Fanrong Li
a34aa63685
[https://nvbugs/5767223][feat] add pp support for DeepSeek-v3.2 (#10449) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-07 12:29:51 +08:00
xinhe-nv
1fbadd2dde
[None][chore] Add failed cases into waives.txt (#10365) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Jie Li <lijie@nvidia.com>
Signed-off-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
Co-authored-by: Jie Li <lijie@nvidia.com>
Co-authored-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
 2026-01-06 22:08:06 -05:00
Ivy Zhang
4a1b2e23b3
[https://nvbugs/5698434][test] add qwen3-4b accuracy test case (#10382) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2026-01-06 21:56:34 -05:00
Lucas Liebenwein
6095c80e56
[https://nvbugs/5721907][fix] AutoDeploy: improve numerical stability of flashinfer attention test (#10467) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-06 21:11:06 -05:00
Zongfei Jing
bb2f883296
[None] [feat] Add test script and raster M for gather fc1 kernel (#10429) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2026-01-07 09:31:49 +08:00
Lucas Liebenwein
bb6a3973aa
[https://nvbugs/5732942][fix] AutoDeploy: handle transformers 4.57.1 upgrade fixes (#10466) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-06 19:55:49 -05:00
Mike Iovine
77be1b7572
[https://nvbugs/5749988][fix] Remove redundant qwen3 spec dec test (#10387) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-06 11:46:34 -05:00
Enwei Zhu
037753f65b
[https://nvbugs/5748600][ci] Unwaive disagg guided decoding test (#10409) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-06 11:38:12 -05:00
JunyiXu-nv
7d62773c6c
[https://nvbugs/5760726][fix] Use random port in container port section (#10432) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2026-01-06 23:25:46 +08:00
xinhe-nv
704f58dfbe
[TRTLLM-8638][fix] Add failed cases into waives.txt (#10427) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-06 04:47:54 -05:00
Emma Qiao
6507087c3f
[None][infra] Waive failed cases on 1/6 (#10440) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-06 16:54:54 +08:00
Bo Li
df0b976b99
[https://nvbugs/5785206][infra] Waive TestQwen3_30B_A3B::test_fp8[latency-torch_compile=False]. (#10441) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2026-01-06 03:32:19 -05:00
William Zhang
ab58d7cac1
[https://nvbugs/5772361][ci] Unwaive tests that have been fixed (#10424) 
These tests were all failing due to the same issue, and were fixed
in #10394.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2026-01-05 23:49:54 -08:00
Ivy Zhang
1e828587e5
[TRTLLM-9896][test] add vswa test cases coverage (#10146) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2026-01-06 02:02:29 -05:00
Yiqing Yan
5108a69fc0
[TRTLLM-9622][infra] Enable DGX_B300 multi-gpu testing in pre-merge pipeline (#9699) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2026-01-06 14:39:55 +08:00
xinhe-nv
998527724c
[TRTLLM-8638][fix] Add failed cases into waives.txt (#10367) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-06 01:09:21 -05:00
Ivy Zhang
22a1d31a27
[None][test] update test case constraint (#10381) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2026-01-06 12:28:59 +08:00
xinhe-nv
1b1058279c
[TRTLLM-8638][fix] Add failed cases into waives.txt (#10384) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-05 23:02:27 -05:00
kris1025
3e98265682
[None][chore] unwaive qwen3 30b test (#10115) 
Signed-off-by: linquanh <linquanh@nvidia.com>
 2026-01-06 11:17:08 +08:00
alel
6b8ae6fa81
[None][feat] CuteDSL MOE FC1 Enhancement (#10088) 
Signed-off-by: Yuhan Li <51736452+liyuhannnnn@users.noreply.github.com>
 2026-01-06 09:30:43 +08:00
chenfeiz0326
8a04c05079
[None][fix] Only Use Throughput Metrics to Check Regression (#10404) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2026-01-06 09:21:15 +08:00
Chuang Zhu
536a8f6a9c
[TRTLLM-9527][feat] Add transferAgent binding (step 1) (#10113) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2026-01-06 08:40:38 +08:00
Simeng Liu
3b56548fcf
[https://nvbugs/5777044][chore] Remove solved bugs from waives.txt (#10422) 
Signed-off-by: Simeng Liu <109828133+SimengLiu-nv@users.noreply.github.com>
 2026-01-05 16:56:58 -05:00
Mike Iovine
91ff46d418
[https://nvbugs/5745152][fix] Unwaive gpt oss spec decode test (#10370) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-05 16:06:58 -05:00
Mike Iovine
7a2dab8e85
[https://nvbugs/5695984][fix] Unwaive llama3 eagle test (#10092) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-05 16:03:35 -05:00
Yan Chunwei
6b71b03947
[TRTLLM-9551][infra] Partition test_llm_pytorch.py for parallel execution (#10400) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2026-01-05 13:58:03 -05:00
Mike Iovine
db2614ef10
[https://nvbugs/5772414][fix] Fix draft token tree depth=1 corner case (#10385) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-05 17:20:14 +01:00
Gal Hubara-Agam
e98c27ee4f
[TRTLLM-10053][feat] AutoDeploy: Add Super v3 config file, improve test runtime (#10397) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-01-05 18:17:27 +02:00
Anthony Chang
225d3a9001
[None][perf] TRTLLM MoE maps to lower tuning buckets when ep>1 (#9998) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2026-01-05 17:16:12 +01:00
Balaram Buddharaju
a792c23dcf
[TRTLLM-9465][fix] Swap TP-CP grouping order (#10350) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-05 20:08:03 +08:00
xinhe-nv
b1733d56f6
[TRTLLM-9381][test] add disag-serving kimi k2 thinking tests (#10357) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2026-01-05 05:15:52 -05:00
Fanrong Li
4931c5eb3a
[None][feat] update deepgemm to the DeepGEMM/nv_dev branch (#9898) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-05 16:43:42 +08:00
Yukun He
d272f1a9bc
[TRTLLM-8821][feat] Apply AutoTuner to AllReduce Op for strategy tuning. (#8531) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-05 15:44:37 +08:00
HuiGao-NV
2f768b76f8
[https://nvbugs/5715568][fix] Force release torch memory when LLM is destroyed (#10314) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2026-01-05 15:30:18 +08:00
Emma Qiao
c63fad7d96
[None][infra] Waive failed cases again on 1/5 (#10403) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-05 02:12:16 -05:00
Yihan Wang
e7a4486294
[https://nvbugs/5752521][fix] Unwaive test_trtllm_flashinfer_symbol_collision.py (#10227) 
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
 2026-01-05 14:37:05 +08:00
Yukun He
0937df2c68
[TRTLLM-10185][feat] AutoTuner Cache: Support cache file lock and merge all ranks into one (#10336) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-05 13:44:09 +08:00
Emma Qiao
5a8bfcbb50
[None][infra]Waive failed cases in post-merge on 1/5 (#10399) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-05 12:30:10 +08:00
Tailing Yuan
a7fe043b13
[None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2026-01-05 11:23:04 +08:00
Yuxian Qiu
5773a4d775
[https://nvbugs/5701425][chore] Unwaive tests. (#10269) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-05 09:54:26 +08:00
Fanrong Li
b5a1e10bc0
[https://nvbugs/5779534][fix] fix buffer reuse for CUDA graph attention metadata (#10393) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-05 09:43:44 +08:00
Wanli Jiang
da0830670a
[TRTLLM-10065][feat] Add accuracy tests for super-v3 with multiple-gpus (#10234) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2026-01-05 09:41:49 +08:00
Lizhi Zhou
82c1ba84a7
[https://nvbugs/5649010][fix] use 0 port as arbitrary port when disagg service discovery is enabled (#10383) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-05 09:40:40 +08:00
Eran Geva
e2f5455533
[#8391][chore] added deepseek_r1_distill_qwen_32b AutoDeploy perf test to L0 (#10377) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-04 20:35:52 +02:00
chenfeiz0326
a65b0d4efa
[None][fix] Decrease Pre Merge Perf Tests (#10390) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-04 12:21:34 -05:00
Yanchao Lu
c4f27fa4c0
[None][ci] Some tweaks for the CI pipeline (#10359) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-04 11:10:47 -05:00
dongfengy
afc533193d
[None][feat] Support nvfp4 for gptoss (#8956) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2026-01-04 08:57:44 -05:00
Jaedeok Kim
a4dcc6a711
[TRTLLM-10171][fix] Correct attention handling in ModelConfig and KVCacheManager (#10330) 
Signed-off-by: Jaedeok Kim <jaedeokk@nvidia.com>
 2026-01-04 06:07:30 -05:00
Yuxian Qiu
6ba04eba06
[https://nvbugs/5748683][fix] Use get_free_port_in_ci to avoid port conflict. (#10392) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-04 19:04:58 +08:00
Yanchao Lu
c0b3c2b919
[None][ci] Remove an invalid test waive 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-03 23:34:13 +08:00
Emma Qiao
865992b86b
[None][infra] Waive failed cases on 1/3 (#10391) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2026-01-03 05:54:09 -05:00
Izzy Putterman
bdf6953ddc
[None][feat] Eagle: MLA Based Eagle (#9677) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2026-01-02 13:45:07 -05:00
Gal Hubara-Agam
f3dd6da080
[#10056][chore] AutoDeploy: Enable Nemo SuperV3 accuracy test (#10308) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-01-02 11:20:19 +02:00
chenfeiz0326
5e0e48144f
[None][fix] Minor updates on Perf Test System (#10375) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2026-01-02 17:17:42 +08:00
fredricz-20070104
f631b25c85
[None][test] Unified slurm extra args management and session collection logic (#10332) 
Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
Signed-off-by: yingguo-trt <244492186+yingguo-trt@users.noreply.github.com>
Co-authored-by: yingguo-trt <244492186+yingguo-trt@users.noreply.github.com>
 2026-01-01 21:10:51 -05:00
Balaram Buddharaju
4a1b742aa0
[TRTLLM-9467][fix] Fix PP+CP combination with helix parallelism (#10312) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-01 13:42:53 -05:00
Balaram Buddharaju
9f5b750a93
[None][chore] Waive tests blocking pre-merge 12/31 (#10373) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-01 03:00:24 -05:00
Balaram Buddharaju
0b75340223
[https://nvbugs/5744427][fix] Make Gemma3 multimodal test fp8 (#10368) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-01 01:11:34 -05:00
Yuxian Qiu
ff836d4f41
[https://nvbugs/5740359][chore] Unwaive tests. (#10260) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-01 09:53:34 +08:00
Lucas Liebenwein
1bbe71b3ed
[#10244][feat] AutoDeploy: separate prefill/decode in flashinfer (#10252) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-31 17:01:24 -05:00
Simeng Liu
84d107b2f0
[https://nvbugs/5717993][fix] Add execution_stream across PyExecutor, KVCacheManager, PeftCacheManager to ensure proper CUDA stream synchronization between KV cache transfer operations and model forward kernels. (#10060) 
Signed-off-by: SimengLiu-nv <simengl@nvidia.com>
 2025-12-31 09:22:54 -08:00
xinhe-nv
0d2e2718ce
[None][chore] Add failed cases into waives.txt (#10354) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-31 09:30:22 -05:00
chenfeiz0326
a23c6f1092
[TRTLLM-9834][feat] Transfer to TRTLLM-INFRA Database and Fail post-merge tests if regression (#10282) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2025-12-31 21:44:59 +08:00
tcherckez-nvidia
464847c6be
[#9717][chore] Standardize MoE weights interface (#10295) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2025-12-31 07:37:18 -05:00
Jin Li
ef1d4a40b5
[https://nvbugs/5727475][fix] Avoid use property with setter in nn.Mo… (#10212) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-31 06:21:36 -05:00
Emma Qiao
d944430f96
[None][infra] Waive failed cases on 12/31 (#10353) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-31 17:39:49 +08:00
Necofish
73870ae4ad
[None][feat] support Qwen3-VL dense model in pytorch backend (#9060) 
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
 2025-12-31 17:54:26 +09:00
xinhe-nv
827d12caaf
[https://nvbugs/5558516][test] add disaggregated stress test (#9354) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-31 16:47:36 +08:00
Yuxian Qiu
910a633066
[https://nvbugs/5774869][chore] waive tests. (#10356) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-31 03:00:52 -05:00
xinhe-nv
1e9c153b4c
[None][fix] disable thread leak check for kimi (#10337) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-31 01:31:37 -05:00
xinhe-nv
6c1abf2d45
[None][chore] Add failed cases into waives.txt (#10344) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-31 00:11:54 -05:00
Jin Li
34c2fd50a9
[https://nvbugs/5707359][fix] Unwaive OOM case that should be fixed by #9446 (#10334) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-31 10:41:39 +08:00
Yuxian Qiu
ec8a388c25
[https://nvbugs/5769890][fix] Import get_free_port. (#10341) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-31 09:47:27 +08:00
Eran Geva
74832a1895
[https://nvbugs/5766986][fix] fixed the shard_all_unprocessed default value to align with the default.yml (#10271) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-30 08:54:13 -05:00
Bo Li
1f0365da36
[None][infra] Add LongBenchV1 to trtllm-eval. (#10265) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-30 21:39:34 +08:00
Emma Qiao
6732c76414
[None][infra] Waive failed cases for main on 12/30 (#10338) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-30 05:17:43 -05:00
Emma Qiao
fb05cd769a
[None][infra] Enable single-gpu CI on spark (#9304) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
Signed-off-by: Jenny Liu <JennyLiu-nv+JennyLiu@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-30 17:22:14 +08:00
Emma Qiao
cce7247815
[https://nvbugs/5594703][infra] Unwaive the failed case to test (#10275) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-30 16:38:54 +08:00
xinhe-nv
6accdbc6a6
[None][chore] Add failed cases into waives.txt (#10302) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-30 03:11:52 -05:00
ruodil
0f4ed90560
[TRTLLM-9965][test] add long-context disagg test for GB300/GB200 and remove config_index in yaml (#10225) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
 2025-12-30 02:39:50 -05:00
xinhe-nv
3e0344a53d
[None][chore] Add failed cases into waives.txt (#10301) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-30 14:04:28 +08:00
xinhe-nv
48fee8d0f6
[None][chore] Add failed cases into waives.txt (#10321) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-30 00:11:49 -05:00
Emma Qiao
f396ad83b0
[None][infra] Remove duplicates in waives.txt (#10333) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-29 22:32:52 -05:00
Balaram Buddharaju
4944192eae
[None][chore] Waive tests failing in pre-merge 12/28 (#10311) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-29 20:53:49 -05:00
Neta Zmora
966231d29c
[#9626][feat] Add an auto-deploy transform for using cutlass FP4 MoE kernels (#10304) 
Add a transform to relace torch.ops.auto_deploy.torch_quant_nvfp4_moe
with the optimized torch.ops.auto_deploy.trtllm_quant_nvfp4_moe_fused.

Currently generates the wrong results when the number of rows in MoE FC1 weights is not divisible by 128,
so torch.ops.auto_deploy.trtllm_quant_nvfp4_moe_fused is not set as the default FP4 MoE implementation (i.e. the transform is disabled).

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-29 23:18:15 +02:00
Yueh-Ting (eop) Chen
9cee32ab39
[https://nvbugs/5625990][fix] Respect VSWA scheme when doing block store for reuse and load block for reuse in KV cache manager (#10183) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-12-29 14:29:14 +08:00
Yanchao Lu
2f8d6d25a8
[None][ci] Waive an intermittent test hang case (#10324) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-29 13:04:31 +08:00
Yanchao Lu
270be801aa
[None][ci] Move remaining DGX-B200 tests to LBD (#9876) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-28 13:55:39 +08:00
JunyiXu-nv
55bc6a5ff8
[https://nvbugs/5753250][fix] Fix undefined local variable in responses utils (#10154) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
Signed-off-by: JunyiXu-nv <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-28 06:59:32 +08:00
shivghai
ee07a7c55e
[None][fix] [Gemma3] Fix RoPE for local attention for Gemma3 (#9961) 
Signed-off-by: Shiv Ghai <8965168+shivghai@users.noreply.github.com>
 2025-12-27 11:50:59 -08:00
Guoming Zhang
93ac0bc1dc
[TRTLLM-10126][feat] Increase topk upper limit to 22 for NVLinkOneSid… (#10229) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-12-27 22:48:10 +08:00
Jin Li
c04563657e
[TRTLLM-7735][feat] Attention NVFP4 out support for torch compile (#9740) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-27 00:07:20 +08:00
chenfeiz0326
d70aeddc7f
[TRTLLM-8952][feat] Support Multi-Node Disagg Perf Test in CI (#9138) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2025-12-26 22:50:53 +08:00
Pengyun Lin
684b37df02
[https://nvbugs/5747938][fix] Use local tokenizer (#10230) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-26 22:08:10 +08:00
Pengyun Lin
c5b0f9e436
[https://nvbugs/5633700][fix] Cache tiktoken vocab for gpt-oss (#10219) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-26 18:39:03 +08:00
dongfengy
bfc591994c
[https://nvbugs/5745152][fix] Fix some GPTOSS test setups (#10085) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2025-12-26 17:52:40 +08:00
Neta Zmora
f3f02315df
[None][chore]: small refactoring to auto-deploy MoE operator (#10300) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-25 12:27:11 -05:00
bhsueh_NV
db3430f589
[None][feat] Support VLM part for Mistral Large 3 (#10188) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-12-25 11:20:58 -05:00
Ziyi Xiong
d8b5aeb061
[https://nvbugs/5652062][fix] Rewind kv_cache and reset draft tokens (#10160) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-25 09:13:51 -05:00
ZhichenJiang
46e4af5688
[TRTLLM-9831][perf] Enable 2CTA with autotune for CuteDSL MoE and Grouped GEMM optimizations (#10201) 
Signed-off-by: zhichen jiang <zhichenj@NVIDIA.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-25 09:04:20 -05:00
Lizhi Zhou
fe12faef81
[https://nvbugs/5752516][chore] unwaive test; fix port conflicts in CI (#10152) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-12-25 08:16:09 -05:00
Emma Qiao
0ecdb69b93
[None][infra] Waive failed tests for main on 12/25 (#10298) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-25 05:22:39 -05:00
Jie Li
83e02ee335
[None][chore] Remove NIM TRT-Backend Test Lists (#10232) 
Signed-off-by: Jie Li <lijie@nvidia.com>
 2025-12-25 04:01:51 -05:00
Enwei Zhu
182b3eb633
[None][ci] Waive TestLlama3_1_8B::test_auto_dtype[False-2] for timeout (#10293) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-25 02:35:18 -05:00
Gabriel Wu
1d01214ff0
[None][feat] Drop non-deepgemm fp8 block scale gemm (#10256) 
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
 2025-12-25 14:52:52 +08:00
xinhe-nv
4ae6f6a46c
[None][chore] Add failed cases into waives.txt (#10249) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-25 01:26:21 -05:00
Venky
c059e6caa1
[TRTC-121] [feat] Add recipe selector UI to complement the recipe database (#10125) 
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
 2025-12-24 23:56:54 -05:00
gramnarayan
a9eb5afc9f
[#9241][feat] AutoDeploy: Support Eagle3 Speculative Decoding (#9869) 
Support two model flow with no overlap scheduler or chain drafter. Drafting model is in PyTorch backend.

Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2025-12-24 23:30:42 -05:00
Emma Qiao
16fd781e42
[TRTLLM-9862][infra] Move single-gpu tests on rtxpro6000d to pre-merge (#9897) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-24 21:45:33 -05:00
Neta Zmora
c4b36d31ff
[#10137][feat] AutoDeploy FP8 MoE refactor (#10138) 
The trtllm (cutlass) fp8 moe operator performs W3+W1 fusion (concat) during inference and we want to move this fusion to the model optimization time.

The Cutlass MoE kernel is used thru a trtllm torch operator.
Its implementation uses two FC operations (fc1 and fc2) while the canonical MoE API defines three GEMM operations and their associated weights (W1, W2, W3) so when we switch from the torch.moe op to the trtllm.moe op we also change terminology from w1, w2, w3 to fc1, fc2.

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-24 18:58:10 +02:00
Stanley Sun
ddac4d7379
[None][test] Add disag-serving auto scaling qa test (#10262) 
Signed-off-by: Stanley Sun <stsun@nvidia.com>
 2025-12-24 08:43:47 -05:00
shuyixiong
f4f0fe85e9
[TRTLLM-9737][chore] Add rl perf reproduce script and enhance the robustness of Ray tests (#9939) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-12-24 15:27:01 +08:00
xinhe-nv
534700ecd9
[None][chore] Add failed cases into waives.txt (#10240) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-24 02:21:50 -05:00
Fanrong Li
156f6453dc
[TRTLLM-9798][feat] Change to use new DeepGEMM MQA sm100 kernel for MTP-3 (#10226) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-24 14:39:12 +08:00
Emma Qiao
7b84e48e0f
[None][infra] Waive failed cases om 12/24 (#10257) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-23 22:49:57 -05:00
xinhe-nv
fc1f77eafc
[None][chore] Add failed cases into waives.txt (#10204) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
Co-authored-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
 2025-12-24 10:37:23 +08:00
Balaram Buddharaju
8c1cfc872b
[TRTLLM-9493][feat] Custom AllToAll for helix parallelism (#9986) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-23 18:14:30 -08:00
Jhao-Ting Chen
92d90fa29a
[None][feat] Expose enable_trt_overlap in Triton_backend brings 1.05x OTPS (#10018) 
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
 2025-12-23 11:41:31 -06:00
Grzegorz Kwasniewski
0027a01ad5
[https://nvbugs/5680312][fix] Updated test waiving (#9630) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-12-23 09:38:12 -08:00
Emma Qiao
984c20e0b2
[None][infra] Waive failed cases on 12/23 (#10236) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-12-23 08:48:54 -05:00
dongfengy
e284d0bf80
[None][infra] Waive flaky unittest/executor/test_rpc_proxy.py and unittest/executor/test_rpc_worker.py tests (#10209) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-23 07:43:13 -05:00
Yukun He
522f1d2bc3
[https://nvbugs/5764627][chore] waive the time-out test (#10222) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-23 16:36:06 +08:00
Balaram Buddharaju
f2e00a75de
[None][chore] Remove helix test from rtx test list (#10224) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-23 03:07:37 -05:00
Shiyu Li
3ddc9d2b48
[https://nvbugs/5729697][fix] MNNVL Allreduce: use CUDA runtime instead of Macro to get SM version. (#10062) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-12-23 16:07:07 +08:00
chenfeiz0326
48c875f8ea
[None][fix] Add OpenSearch URL in slurm_launch.sh for Multinode Perf Sanity Test (#9990) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2025-12-23 16:02:38 +08:00
Bo Li
cc1323be24
[None][fix] Fix the bug for top_k=10 in NVLinkOneSided AlltoAll. (#10197) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-23 02:13:37 -05:00
Chuang Zhu
53db3b2612
[https://nvbugs/5741884][fix] unwaive disagg sampler (#10189) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-12-23 14:38:07 +08:00
xinhe-nv
77b591f73b
[None][chore] Add failed cases into waives.txt (#10177) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Jie Li <lijie@nvidia.com>
Signed-off-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
Co-authored-by: Jie Li <lijie@nvidia.com>
Co-authored-by: Jie Li <76780849+jieli-matrix@users.noreply.github.com>
Co-authored-by: Larry Xu <197874197+LarryXFly@users.noreply.github.com>
 2025-12-23 13:43:50 +08:00
Harshini Komali
d691371eaf
[TRTLLM-9091] [feat] Replace GenAI-Perf with AIPerf (#9310) 
Signed-off-by: lkomali <lkomali@nvidia.com>
Signed-off-by: Harshini Komali <157742537+lkomali@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-12-23 13:25:55 +08:00
Pamela Peng
5bc7ffe379
[None][test] Add qa tests for RTX 6K (#10210) 
Signed-off-by: Pamela <179191831+pamelap-nvidia@users.noreply.github.com>
 2025-12-22 22:47:09 -05:00
fredricz-20070104
621156ad44
[None][chore] Fix GB300 support issues (#10196) 
Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
Signed-off-by: fredricz-20070104 <226039983+fredricz-20070104@users.noreply.github.com>
 2025-12-23 10:42:41 +08:00
Yuxian Qiu
696f754ef4
[None][fix] avoid implicit cudaStreamSynchronize in sample_async. (#10120) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-23 10:15:40 +08:00
Fanrong Li
0d2500c631
[TRTLLM-9677][feat] Support DeepSeek-V3.2 tool parser (#10126) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-23 08:46:47 +08:00
tcherckez-nvidia
12e1cb8d7e
[#9717][chore] Refactor MoE code to use enums (#9910) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2025-12-22 15:14:56 -05:00
JunyiXu-nv
aaa87abf41
[TRTLLM-7906][feat] Support multiple post process for Responses API (#9908) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-22 11:33:34 -05:00
Emma Qiao
ba14a9308e
[None][infra] Waive failed cases on 12/22 (#10200) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-12-23 00:05:45 +08:00
Pengyun Lin
0f308e95f9
[None][chore] Remove logprobs constraint on trtllm-serve pytorch backend (#9911) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-22 21:37:22 +08:00
William Zhang
a6a88985cf
[TRTLLM-9409][feat] Pass MRoPE tensors for EPD disagg (#9758) 
* Why?

Certain VLMs like the Qwen family need more than just the multimodal
embeddings in the language model, and need MRoPE position IDs and
deltas. Prior to this commit, only the embeddings could be communicated
from the encoder worker to the prefill worker.

* What?

This commit extends the `DisaggregatedParams` to include the MRoPE
information. It also adjusts several pieces of code required to
communicate that between E, P and D workers.

Closes TRTLLM-9409.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-12-22 06:32:49 -05:00
Bo Li
472fe497dc
[None][chore] NVLinkOneSided AlltoAll Support zero local_num_tokens. (#9822) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-22 05:57:12 -05:00
Yan Chunwei
ea6cd76c55
[None][refactor] simplify get_stats and get_kvcache_events with rpc (#9980) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-12-22 18:23:43 +08:00
Perkz Zheng
c87f1a6b39
[https://nvbugs/5503479][fix] update trtllm-gen kernels to address few bugs (#10089) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-12-22 04:45:33 -05:00
shuyixiong
9e9523c3cc
[https://nvbugs/5762016][chore] Skip a ray test (#10194) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-12-22 17:06:19 +08:00
xinhe-nv
d30ee8101e
[None][chore] Remove closed bugs (#10182) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-12-22 01:58:17 -05:00
Yuxian Qiu
237fd0eae4
[https://nvbugs/5666821][chore] unwaive tests. (#9958) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-22 11:39:45 +08:00
Jin Li
066b653940
[TRTLLM-9880][feat] Include torch compile tests in QA test list (#10149) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-22 10:37:09 +08:00
Yuxian Qiu
2f139ee07e
[https://nvbugs/5701445][chore] unwaive test. (#9949) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-22 10:12:54 +08:00