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
3,510 Commits 25 Branches 59 Tags 2.1 GiB
cc12d33393
Commit Graph

3510 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Yi Sun
cc12d33393
[None][feat] Deep Research Implemented with Scaffolding (#8452) 
Signed-off-by: Yi Sun <yisun0618@gmail.com>
 2025-11-06 10:33:28 +08:00
JadoTu
6bbb43f2b9
[None][feat] Add qwen3-next nvfp4 support (#8526) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-11-06 09:45:44 +08:00
Lucas Liebenwein
7a552c450a
[https://nvbugs/5606166][fix] AutoDeploy: unwaive test for use tuples for cudagraph shape lookup (#8957) 
also updated test waive for another nvbug

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-05 16:27:00 -08:00
Frida Hou
fb7f9831d3
[#8924][fix] Fix AutoDeploy pattern matcher for torch 2.9 (#8920) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-05 13:29:20 -08:00
Lucas Liebenwein
b181568d6f
[TRTLLM-8201][feat] Nemotron H MoE Sharding (#8744) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-05 12:35:29 -08:00
Perkz Zheng
222bc911cd
[None][feat] add swapsMmaAb sparseMla kernels (#8913) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-11-05 09:32:34 -08:00
Chang Liu
e57d83c5dc
[TRTLLM-8768][chore] Fuse QK down_proj with indexer K + weight_proj for FP4 ckpt (#8771) 2025-11-05 07:57:09 -08:00
fredricz-20070104
fdd9e4fe00
[TRTLLM-7251][test] Get submit eplb slots empty key work (#8945) 
Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
 2025-11-05 05:21:02 -08:00
Fanrong Li
c2feed798a
[https://nvbugs/5630345][chore] unwaive DS-v32 nvfp4 and fp8 tests (#8887) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-05 03:49:23 -08:00
Chuang Zhu
595f78078c
[https://nvbugs/5624367][fix] Fix disagg GPT-OSS test (#8870) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-11-05 01:47:09 -08:00
Yiteng Niu
1ce83582f9
[None][infra] update github token name (#8907) 2025-11-05 00:55:28 -08:00
Yukun He
b9e5315dfb
[https://nvbugs/5623960][fix] Fix the logger once key issue and further compress log in AutoTuner. (#8873) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-05 15:25:43 +08:00
Emma Qiao
31116825b3
[None][infra] Waive failed cases on main 11/05 (#8936) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-04 22:54:45 -08:00
xinhe-nv
cc4aa29523
[None][chore] Add failed cases into waives.txt (#8865) 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
 2025-11-04 19:26:50 -08:00
Shiyu Li
eeb56c2848
[None][feat] MNNVLAllreduce Kernel Refactor (#8018) 
Signed-off-by: Shiyu Li <timlee0212@outlook.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-11-05 08:49:47 +08:00
Yechan Kim
ed81173c55
[None][ci] Add test on waives (#8915) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-11-05 08:42:08 +08:00
Yibin Li
871ea244a3
[None][chore] Design diagram review process change (#8748) 
Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>
 2025-11-04 16:38:34 -08:00
Patrice Castonguay
782824533e
[https://nvbugs/5587574][fix] Increase server timeout to wait for weight loading (#8806) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-11-04 12:11:08 -08:00
Frida Hou
11ded113cd
[#8389][fix] Update group attention matching to first map to custom torch attention (#8638) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-04 12:00:43 -08:00
shuyixiong
70e4d72ffa
[TRTLLM-8511][feat] Add update_weights and sleep_wakeup support for rl integration (#8302) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
Co-authored-by: Liwei Ma <liweim@nvidia.com>
Co-authored-by: Jonas Yang CN <joyang@nvidia.com>
 2025-11-04 10:19:24 -08:00
Yanchao Lu
e2b2675120
[None][fix] Remove duplicated test waives (#8914) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-04 23:04:33 +08:00
Bo Li
e4bf29bc66
[None][feat] Integrate MnnvlThroughput into TRTLLM MoE. (#8728) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-04 21:36:29 +08:00
Robin Kobus
7e4b87b17c
[None][ci] Remove outdated test entries (#8909) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-04 05:32:46 -08:00
Cao Dong
dddfcdd3bf
[None][fix] Fix bug of undefined py_topk_logprobs_vals (#8789) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-11-04 19:32:59 +08:00
xiweny
cae468cc8e
[https://nvbugs/5596343] [test] Waive flaky GPT-OSS cases (#8904) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
 2025-11-04 03:00:00 -08:00
Zhanrui Sun
4de31bece2
[TRTLLM-8994][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0 (#8838) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-04 18:59:34 +08:00
CarstyYou
4296c9553d
[TRTLLM-1234][feat] Add fp8 blockscaled Gemm for sm120 (#8844) 
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
 2025-11-04 18:10:36 +08:00
Ivy Zhang
23717cdb3f [TRTLLM-8580][test] save runtime report periodically (#8312) (#8455) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
danielafrimi
2b58dba0f6 [https://nvbugs/5524714][fix] Fix TP sharding of fused-QKV weight scales in W4A16 AWQ (#8432) 
Signed-off-by: Daniel Afrimi <dafrimi@nvidia.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
xiweny
ce23e24123 [https://nvbugs/5565565] [fix] Remove waiver (#8450) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Yukun He
6c8ba3be27 [None][chore] Remove duplicate log outputs in test_perf.py (#8418) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
ruodil
102e556863 [None][test] cherry-pick: add test-model-suites in integration conftest.py (#8388) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Yukun He
2225745782 [TRTLLM-8129][feat] Allreduce tuning and benchmark script revising (#7870) 
Because we have encountered some perf regression due to using a one-shot kernel instead of NCCL on A100/H100, it will be beneficial if we can have a solid benchmarking of allreduce Op and analyze the data collected from it.

Implemented new AllreduceOp heuristic:
- Added Linear programming-based heuristic implementation.
- Added LUT-based heuristic implementation and corresponding code generation script.

AllreduceOp minor fixing:
- Fixed a minor issue in AllreduceOp, that the strategy can not be overridden when ONESHOT or TWOSHOT is set.
- Fixed a minor TWOSHOT kernel perf issue.
- Cleaned up Dispatching code in AllReduceOp.

This PR will fix the perf gaps reported in:
https://nvbugspro.nvidia.com/bug/5517023

For Deepseek-R1, it shows a performance gain of about 3-4% in concurrency levels of 256 and 512.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Zhenhuan Chen
34fbc7052c [https://nvbugs/5545522][fix] move PREEXIT in UB kernels to fix accuracy issue (#8318) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Patrice Castonguay
65c138108e [https://nvbugs/5552889][fix] fix: Prevent empty batch when using attention DP with disagg (#8372) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Ivy Zhang
9bcd2e6c0a [None][chore] Update nim test list (#8356) 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Stanley Sun
def9c0004d [TRTLLM-8113][test] Add pytorch workflow e2e tests with pp enabled (#8357) 
Signed-off-by: Stanley Sun <stsun@nvidia.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
xiweny
fcac2022e2 [https://nvbugs/5565565] [fix] fp8 wideep support sm103 (#8228) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Yueh-Ting (eop) Chen
bd1c9c0af4
[https://nvbugs/5625990][chore] Add test coverage for current incapability of the KV cache manager (#8829) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-11-04 16:35:45 +08:00
Yechan Kim
67208f1512
[None][fix] InputProcessor config naming convention fix (#8705) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-11-03 22:29:21 -08:00
Emma Qiao
4fe47faf47
[None][infra] Waive failed tests for main branch (#8897) 
Signed-off-by: qqiao <qqiao@nvidia.com>
 2025-11-03 22:21:28 -08:00
Zhanrui Sun
9ec6a6b68f
[None][infra] waive failed test on main 11/4 (#8896) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-11-03 21:37:09 -08:00
HuiGao-NV
97674c3114
[TRTLLM-8690][feat] add more tensors to share buffers (#8691) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-11-03 21:08:01 -08:00
Yan Chunwei
ed297d7c2e
[None][chore] Optimize perf for the RPC executor and add some profile utilities to llm-api (#8415) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-11-03 17:59:49 -08:00
Anish Shanbhag
6a6317727b
[TRTLLM-8680][doc] Add table with one-line deployment commands to docs (#8173) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-11-03 17:42:41 -08:00
Matthias Jouanneaux
d0f107e4dd
[TRTLLM-5966][feat] Helix: add full MLA support for Helix (#8104) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
 2025-11-04 09:06:58 +08:00
Mike Iovine
5e6f1bcd24
[TRTLLM-8979][test] Improve qwen3 spec dec test coverage (#8767) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-03 10:12:10 -08:00
Matt Lefebvre
0f6763680a
[TRTINFRA-7215][infra] - Move half of the DGX H100 premerge tests to SLURM (#8849) 
Signed-off-by: Matt Lefebvre <mlefebvre@nvidia.com>
 2025-11-04 00:11:26 +08:00
Kaiyu Xie
db2a42f641
[None][chore] Add sample yaml for wide-ep example and minor fixes (#8825) 
Signed-off-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
 2025-11-03 07:48:34 -08:00
Li Min
89336fbf07
[None][fix] Fix cute dsl nvfp4 gemm autotune issue (#8761) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-11-03 22:55:45 +08:00