kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-05 02:31:33 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,838 Commits 28 Branches 65 Tags 2 GiB
ff0dd6076e
Commit Graph

2079 Commits

Author SHA1 Message Date
sunnyqgg
ff0dd6076e
[TRTLLM-10062][feat] Enable MTP for Nemotron Super (#10754) 
Signed-off-by: qgai <qgai@nvidia.com>
 2026-01-26 11:23:26 -05:00
Lucas Liebenwein
00f341be49
[#8982][feat] AutoDeploy attention dp support (#10728) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-26 09:43:33 -05:00
Pengyun Lin
ce37e27066
[#10614][fix] gpt_oss first iteration streaming in trtllm-serve (#10808) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2026-01-26 20:53:11 +08:00
Bo Li
e405468230
[TRTLLM-10048][feat] Fuse the AllGather for expert statistics required by the EPLB. (#10885) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2026-01-26 17:59:03 +08:00
Tian Zheng
5efee01da1
[None][feat] Add Skip Softmax MLA kernels for Blackwell and Fix an accuracy bug of NVFP4 KV (#10813) 
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2026-01-26 16:46:33 +08:00
Enwei Zhu
72ef732bcf
[TRTLLM-10147][perf] Balanced random MoE workload generator for CuteDSL kernel UT, autotuner and layerwise benchmark (#10279) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-25 21:02:30 +08:00
Yanchao Lu
ae58a7ed20 [None][chore] Revert NVIDIA/TensorRT-LLM#10819 (#10870) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
Yanchao Lu
18f63dfcec [None][chore] Reduce tedious logs (#10819) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
mpikulski
0f7ec033f7 [https://nvbugs/5791242][fix] workaround for flashinfer.sampling.sampling_from_logits (#10713) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
Yukun He
25bdc30162 [https://nvbugs/5782112][fix] Cherry-pick #10633: Fix hanging issue for MNNVL Allreduce under PP (#10750) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
Yuxian Qiu
2b3bb2e9b0 [https://nvbugs/5811697][fix] Fix buffer reuse. (#10716) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
Mike Iovine
f02948d956 [https://nvbugs/5803813][fix] Fix llama 4 min latency (#10724) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-01-25 18:12:21 +08:00
Yao Yao
6f07fa81d7
[TRTLLM-7738][feat] Adding implementation of KVCacheManagerV2 (#10736) 
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>

KVCacheManagerV2 is a new python-based implementation of the KV cache manager, featuring cleaner API, better abstraction and better code quality without the accumulated legacy.
 2026-01-24 04:48:39 -05:00
Yuxian Qiu
9fcc93ea7b
[https://nvbugs/5829097][fix] Re-init TRTLLM sampler to use sample stream in multi-stream cases. (#10918) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-24 14:04:10 +08:00
Kaiyu Xie
da967d0bd7
[TRTLLM-10334] [feat] Support overlap scheduler for disagg ctx instances (#10755) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2026-01-23 22:29:37 -05:00
jthomson04
cf88da7eca
[None][feat] KV Connector Support for MTP (#10932) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2026-01-23 18:58:26 -05:00
Taylor Yeonbok Lee
1fbbb1f3cd
[None][feat] AutoDeploy: Enhance memory consumption for MoE fusion transform (#10772) 
Signed-off-by: Taylor Yeonbok Lee <249374542+taylor-yb-lee@users.noreply.github.com>
 2026-01-23 15:22:54 -08:00
Yan Chunwei
54768f3f2c
[None][chore] refine placement group in ray executor (#10235) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2026-01-23 19:31:20 +08:00
Leslie Fang
31d04dfa12
[TRTLLM-9108][feat] Add test configurable moe module multi gpu (#10699) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2026-01-23 10:16:58 +08:00
William Zhang
2146c23786
[#9306][refactor] Refactor AutoDeployConfig into LlmArgs (#10613) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2026-01-22 16:02:49 -05:00
Grzegorz Kwasniewski
d8e6e22060
[https://nvbugs/5819002][fix] fix sharding tests (#10775) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-22 20:02:48 +01:00
Yi Zhang
d43be7b65e
[None][fix] Avoid Double update for previous batch (#9888) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2026-01-22 13:15:06 -05:00
Shi Xiaowei
944c304bbb
[TRTLLM-9527][feat] Python transceiver components (step 2) (#10494) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2026-01-22 10:14:50 -08:00
Venky
b3146d095d
[TRTC-122][feat] Eagle3 Specdec UX improvements (#10124) 
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
 2026-01-22 07:24:11 -08:00
Yan Chunwei
30ffa58b54
[https://nvbugs/5783876][fix] fix hmac launch (#10434) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2026-01-22 23:20:53 +08:00
Pengyun Lin
5e34112b27
[TRTLLM-10388][feat] Support logprobs for Completions API (#10809) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2026-01-22 21:25:24 +08:00
彭晋韬(jtao peng)
9beb971827
[None][fix] Update RMSNorm custom op plumbing (#10843) 
Signed-off-by: jintaop <jintaop@nvidia.com>
 2026-01-22 21:03:22 +08:00
Jiayu Chang
1dc49b266e
[https://nvbugs/5322131][feat] Multi-LoRA serving with CUDA Graph (#8279) 
Signed-off-by: Jiayu Chang <jiayuc@nvidia.com>
 2026-01-22 14:01:18 +01:00
tcherckez-nvidia
128d4ac5be
[None][chore] NVFP4 MoE - Move weights transformation to fusion phase… (#10803) 
Signed-off-by: Tal Cherckez <tcherckez@nvl72070-T11.cm.cluster>
Signed-off-by: Tal Cherckez <tcherckez@nvl72039-T03.cm.cluster>
Signed-off-by: Tal Cherckez <tcherckez@nvl72098-T11.cm.cluster>
Signed-off-by: tcherckez-nvidia <127761168+tcherckez-nvidia@users.noreply.github.com>
Co-authored-by: Tal Cherckez <tcherckez@nvl72070-T11.cm.cluster>
Co-authored-by: Tal Cherckez <tcherckez@nvl72039-T03.cm.cluster>
Co-authored-by: Tal Cherckez <tcherckez@nvl72098-T11.cm.cluster>
 2026-01-22 13:08:05 +02:00
Yiqing Yan
0243abee22
[None][chore] Bump version to 1.3.0rc1 (#10923) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2026-01-22 18:45:40 +08:00
tcherckez-nvidia
6e72aff866
[#10838][fix] Add missing dist strategy param. fix typo for ad_logger… (#10892) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2026-01-22 10:38:31 +02:00
Pengbo Wang
9462d90ec7
[None][feat] Add KV cache cleanup (#7439) 
Signed-off-by: Pengbo Wang <221450789+pengbowang-nv@users.noreply.github.com>
 2026-01-22 15:14:17 +08:00
shuyixiong
fd2af8d58a
[TRTLLM-9771][feat] Support partial update weight for fp8 (#10456) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
Signed-off-by: shuyixiong <219646547+shuyixiong@users.noreply.github.com>
 2026-01-22 14:46:05 +08:00
Enwei Zhu
be4a431ffd
[TRTLLM-10154][feat] Enable guided decoding with reasoning parsers (#10890) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-22 14:14:28 +08:00
Taylor Yeonbok Lee
895bb94b3d
[#8241][feat] Support model_kwargs for pytorch backend (#10351) 
Signed-off-by: Taylor Yeonbok Lee <249374542+taylor-yb-lee@users.noreply.github.com>
 2026-01-21 20:51:38 -08:00
Yechan Kim
70caa779a4
[None][feat] K-EXAONE MTP support (#10796) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2026-01-22 13:43:00 +09:00
Lizhi Zhou
f3a41c8d94
[TRTLLM-10059][feat] Use global unique id as disagg request id (#10187) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-21 22:52:34 -05:00
Daniil
0434db5bf7
[None][feat] GLM-4.5-Air support (#10653) 
Signed-off-by: Daniil Kulko <kulkodaniil@gmail.com>
 2026-01-22 11:42:09 +08:00
dongxuy04
635cbf01ba
[https://nvbugs/5816267][fix] Remove weight tensor holder to release memory earlier (#10876) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2026-01-21 16:42:52 -08:00
Guiju Zhang
8cf8fbbe16
[TRTLLM-10325][feat] Refactor speculative decoding workers (#10768) 
Signed-off-by: Guiju Zhang <7135567+cascade812@users.noreply.github.com>
 2026-01-21 13:05:29 -05:00
xxi
9feebb3a27
[None][chore] switch to ConfigurableMoE as the default path (#10792) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-21 15:57:38 +08:00
Yukun He
a4152c80f6
[https://nvbugs/5814253][fix] unwaive test_autotuner_distributed_strategy tests (#10793) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-21 15:37:11 +08:00
Yukun He
d60d6ff6fd
[None][fix] Cherry-pick #10715: Disable short profile for tunable ops with MERGE strategy (#10844) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-21 13:53:04 +08:00
Yibin Li
9116dfbacd
[https://nvbugs/5775021] [fix] Replace pickle.load with restricted Unpickler (#10622) 
Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>
 2026-01-21 11:42:54 +08:00
Yanchao Lu
ccf4d79c6c
[None][chore] Revert NVIDIA/TensorRT-LLM#10847 (#10869) 2026-01-21 11:08:40 +08:00
Simeng Liu
3c8ed19440
[https://nvbugs/5670108][fix] Fix overlap scheduler race condition in… (#10610) 
Signed-off-by: SimengLiu-nv <simengl@nvidia.com>
 2026-01-20 10:56:56 -08:00
Izzy Putterman
864b61cadd
[None][feat] Speculative One Model: FlashInfer sampling (#10284) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2026-01-20 12:56:43 -05:00
jthomson04
2db3d7eeba
[None][chore] Async Transfer Manager (#9891) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2026-01-20 12:12:47 -05:00
Yanchao Lu
ae8f74b620
[None][chore] Reduce tedious logs (#10847) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-20 22:56:24 +08:00
Grzegorz Kwasniewski
eb326073d8
[TRTLLM-10785][feat] Fix sharding dashboard errors (#10786) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-20 09:25:36 +01:00