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
3,331 Commits 25 Branches 59 Tags 2.1 GiB
2b27810198
Commit Graph

1460 Commits

Author SHA1 Message Date
Daniel Cámpora
9f1d9b7b18
[None][feat] Use list instead of torch tensor for new tokens in update requests (#7730) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-09-23 10:40:08 -04:00
Zheyu Fu
34963ec39c
[None][fix] Assign [] to req.py_draft_tokens instead of None when spec decode is off (#7511) 
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
 2025-09-23 06:54:18 -07:00
ChristinaZ
dd5fb2857a
[None][fix] Re-add the import for allgather that was mistakenly removed. (#7920) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-09-23 03:09:48 -07:00
Yan Chunwei
3ba19b6ff1
[https://nvbugs/5532023][fix] executor with-statement bug (#7895) 
Signed-off-by: chunweiy <chunweiy@nvidia.com>
 2025-09-23 02:05:39 -07:00
Enwei Zhu
f882fb86db
[https://nvbugs/5367180][fix] Fix xgrammar import before loading tensorrt_llm binary (#7906) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-23 00:29:57 -07:00
Yan Chunwei
40820e6711
[None][fix] CHERRY-PICK trtllm-serve yaml loading (#7551) (#7897) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-09-23 14:56:52 +08:00
Pengbo Wang
5792464d37
[None][fix] Read eos_token_id from generation_config for kimi_k2 (#7120) 
Signed-off-by: Pengbo Wang <221450789+pengbowang-nv@users.noreply.github.com>
 2025-09-23 10:47:03 +08:00
yunruis
126cd707e3
[None][opt] Add batch waiting when scheduling (#7416) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
 2025-09-23 10:27:37 +08:00
Chang Liu
998857bcde
[TRTLLM-7328][feat] E-PD Disagg Support via llmapi (3/N) (#7577) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-09-22 19:07:18 -07:00
jianweiwu
9da4203e2e
[None][feat] Add Tencent HunYuanDenseV1 model support (#7081) 
Signed-off-by: sorenwu <sorenwu@tencent.com>
Signed-off-by: jianweiwu <sorenwu@tencent.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-23 09:27:29 +08:00
Tailing Yuan
740340dd17
[https://nvbugs/5522847][fix] Disable GC on disagg server and client (#7858) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-09-23 09:16:55 +08:00
Enwei Zhu
8330d5363a
[TRTLLM-8209][feat] Support new structural tag API (upgrade XGrammar to 0.1.25) (#7893) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-23 09:10:09 +08:00
xxi
d471655242
[TRTLLM-7831][feat] Cherry-pick from #7423 Support fp8 block wide ep cherry pick (#7712) 2025-09-23 08:41:38 +08:00
Enwei Zhu
59f57598a7
[https://nvbugs/5504086][fix] Fix MTP vanilla (#7904) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-23 08:38:28 +08:00
ChristinaZ
be576a3152
[None] [feat] Enable run_post_quant_allgather for MoE TRTLLM backend (#6794) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-09-23 08:24:21 +08:00
Jin Li
b5391b4ac6
[https://nvbugs/5516665][fix] Fix CUTLASS moe fake impl errors (#7714) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-09-22 11:08:39 -07:00
Wanli Jiang
2a30f11d63
[None][chore] Upgrade transformers to 4.56.0 (#7523) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-22 22:20:16 +08:00
Yechan Kim
f77aca9f2c
[TRTLLM-7385][feat] Optimize Qwen2/2.5-VL performance (#7250) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-09-22 03:40:02 -07:00
HuiGao-NV
0dac1ddb74
[https://nvbugs/5525849][fix] Cherry-pick to fix mismatch of max seq len between kv cache manager and dummy requests (#7855) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-09-22 18:07:47 +08:00
Yukun He
ab26d21620 [https://nvbugs/5517023][fix] Pass allreduce strategy and force NCCL on pre-Blackwell arch (#7768) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Yan Chunwei
ba2864a2c6 [None][doc] Enhance api reference doc by labeling stable APIs (#7751) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Yi Zhang
f9c9c3f50a [https://nvbugs/5355219][fix] Fix trtllm moe backend test config and Qwen3 MoE multi node (#7724) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
HuiGao-NV
af34c9713a [https://nvbugs/5474169][fix] seq_len mismatch between kv cache manager and graph attn metadata (#7606) 
Signed-off-by: Hui Gao <huig@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Yukun He
3cc16c2438 [https://nvbugs/5496960][fix] Fix Gemma model forward. (#7509) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Yuxian Qiu
2d46dda6a7 [https://nvbugs/5448754][fix] Download HF model for all nodes. (#6824) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
HuiGao-NV
123f5cbbf0 [https://nvbugs/5474169][fix]Adjust max seq len for kvcache for memory estimation (#7391) 
Signed-off-by: Hui Gao <huig@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Bo Li
a15f08db3d [https://nvbugs/5467548][fix] DeepSeek illegal memory access. (#7298) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-22 14:28:38 +08:00
Stefan Niebler
8aead224fb
[https://nvbugs/5513423][fix] Correctly respect min_tokens in PyTorch Workflow (#7808) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Co-authored-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
 2025-09-21 22:15:18 -07:00
dongxuy04
b057fc9593
[None][fix] cherrypick to main: Fix possible mpi broadcast and gather issue on large object (#7854) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-09-22 10:17:23 +08:00
Enwei Zhu
639d4109a7
[None][fix] Disable torch.compile for CapturableGuidedDecoder (#7871) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-22 10:04:30 +08:00
dongxuy04
9eb8084ca9
[TRTLLM-7008][fix] cherrypick to main Add automatic shared memory delete if already exist (#7727) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-09-21 11:01:51 -07:00
Ziyi Xiong
897c4dd23b
[https://nvbugs/5517404][fix] Use the correct cuda graph for dynamic spec dec (#7728) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-09-21 08:20:48 +08:00
Yan Chunwei
4509d97780
[TRTLLM-8188][chore] refactor GenerationExecutorWorker with WorkerBase for better code reusing (#7840) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-09-20 06:24:22 -07:00
Grzegorz Kwasniewski
8adaf0bb78
[TRTLLM-6342][feat] Support for partial sharding from factory (#7393) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Signed-off-by: Grzegorz Kwasniewski <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-09-19 09:07:42 -07:00
Matthias Jouanneaux
1be7faef37
[TRTLLM-5966][feat] Helix: add custom position ids to MLA kernels (#6904) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
 2025-09-19 20:55:32 +08:00
Liao Lanyu
18095a7cb8
[https://nvbugs/5503440][fix] Fix potential hang due to wrong type of ZMQ socket and protocol for worker_init_status_queue (#7646) 
Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
 2025-09-19 18:13:33 +08:00
Gabriel Wu
0e72e8f7e6
[None][feat] Support EPLB in Qwen3 MoE (#7443) 
Signed-off-by: Gabriel Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-09-19 16:45:35 +08:00
QI JUN
f1b362faac
[None][chore] polish error message in cute_dsl_utils.py (#7852) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-09-19 12:05:11 +08:00
HuiGao-NV
a6370fd143
[https://nvbugs/5481434][feat] cherry-pick fix to reuse pytorch memory segments occupied by cudagraph (#7747) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-09-19 10:25:21 +08:00
Yuxian Qiu
d6ebcf7c4a
[TRTLLM-6994][feat] FP8 Context MLA integration (Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/6059 from release/1.1.0rc2) (#7610) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-09-19 09:40:49 +08:00
Ziyi Xiong
420f0fbcf5
[https://nvbugs/5522851][fix] Correct the logic to update kv_lens_cuda (#7790) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-09-19 08:11:29 +08:00
sunnyqgg
80dd8fe197
[TRTLLM-6746][feat] Enable two-model spec dec for MTP Eagle (#7001) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-09-18 12:05:36 -04:00
Li Min
d921fc3352
[TRTLLM-6898][feat] Add swapab, tileN64, cga sync support for cute dsl nvfp4 gemm (#7764) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-09-18 21:20:04 +08:00
bhsueh_NV
c65457db8a
[None][fix] Revert "Revert "[None][feat] support attention dp for qwen3 dense model"" (#7780) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-09-18 20:11:05 +08:00
Wanli Jiang
fe104dc20d
[TRTLLM-7918][feat] Support kvcache reuse and chunk prefill for phi4mm (#7723) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-09-18 17:37:16 +08:00
Stefan Niebler
a55251bf75
[None][fix] Add TP information in weight scale loading in WeightOnlyQuantLinearMethod (#7732) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-09-18 10:30:50 +02:00
Wanli Jiang
a7ca0fff54
[TRTLLM-6577][feat] Support nano_v2_vlm in pytorch backend (#7207) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-09-18 16:26:20 +08:00
Leslie Fang
870cfcf9a0
[None][chore] Remove executor config in create_py_executor (#7599) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-18 14:24:58 +08:00
mpikulski
1c7f601265
[https://nvbugs/5508890][fix] gen. result cleanup when using PostprocWorker (#7771) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-09-18 14:01:18 +08:00
Li Min
14e455da3e
[None][fix] Fix CI issue for dsl pkg install (#7784) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-09-18 13:58:20 +08:00
Barry Kang
4f0e6b5f96
[None][feat] Cherry-pick DeepGEMM related commits from release/1.1.0rc2 (#7716) 
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-09-18 13:51:48 +08:00
Ziyi Xiong
28469dbf27
[https://nvbugs/5523080][fix] Correct the batch index in device tensors (#7803) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-09-18 13:45:37 +08:00
Guoming Zhang
e0423bfaab
[https://nvbugs/5519544][fix] fix invalid expression for disabling pa… (#7806) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-09-18 12:54:52 +08:00
Yanchao Lu
f8e811d134
[None][chore] Version bump for 1.1.0rc6 (#7824) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-09-18 11:13:56 +08:00
Yukun He
cd80e0a7f1
[None][fix] Make tile_tokens_dim calculation just in time before kernel launching. (#7529) 
tile_tokens_dim directly depends on the num_token, which is a dynamic shape during tuning and inference. When AutoTuner prepares dummy tensors with different num_tokens, it does not update the value of tile_tokens_dim automatically. Therefore, the value stored in the AutoTuner cache is misaligned, which will introduce a lot of cache misses during inference, which hurts perf a lot.

To avoid this issue, we move the calculation of tile_tokens_dim right before kernel launching, so that the value of tile_tokens_dim is always up to date with the num_tokens of the current input tensor used for the kernel runner.

Also, the tile_tokens_dim is calculated based on the number of tokens of a tuned bucket, instead of the original token number. Because we only tune the value for the buckets, not for the raw input token number, to avoid unexpected misalignment between tile_tokens_dim and the token number.

This PR also removes the warmup requests with the extra input shapes, which are triggered in the CUDA graph warmup phase.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-09-18 10:58:52 +08:00
Lucas Liebenwein
39eb120b96
[#7308] [feat] AutoDeploy: graph-less transformers mode for HF (#7635) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
 2025-09-18 10:44:24 +08:00
Netanel Haber
a5cfc8368f
[https://nvbugs/5508536][fix] Revert #7041: Move stop_criteria to sample_async (#7041) (#7796) 
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Mike Iovine <miovine@nvidia.com>
 2025-09-17 21:27:01 -04:00
William Zhang
2614d71994
[TRTLLM-7410][feat] Enable KV cache reuse and chunked prefill for mistral3.1 (#7628) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-09-17 08:11:16 -07:00
Zhenhuan Chen
6983e8a00d
[https://nvbugs/5517260][fix] move scaffolding contrib module's import to subdirectory (#7758) 
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-09-17 11:36:33 +08:00
Kaiyu Xie
62042a9733
[TRTLLM-6741] [feat] enable LM tp for MTP, under attention dp case (cherry-pick #7128) (#7571) 
Signed-off-by: Cheng Hang <chang@nvidia.com>
Co-authored-by: Cheng Hang <chang@nvidia.com>
 2025-09-17 09:41:32 +08:00
Yukun He
6313c9799c
[https://nvbugs/5488582][fix] Cherry-pick 7495: Avoid unexpected Triton recompilation in DG fused_moe (#7708) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-09-17 09:00:28 +08:00
Shiyu Li
8bdbb48264
[https://nvbugs/5489015][fix] Support communicator split in MNNVL allreduce and fix the binding issues. (#7387) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-09-17 07:43:20 +08:00
HuiGao-NV
a49cfb3e68
[https://nvbugs/5516666][fix] cherrypick fix to the CUDA graph warmup issue when using speculative decoding (#7737) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
Co-authored-by: Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-09-17 06:24:20 +08:00
Aurelien Chartier
471723bce1
[None][chore] Remove unused get_quant_scales methods (#7687) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-09-16 12:56:11 -07:00
Lucas Liebenwein
9befd1a72f
[None][chore] AutoDeploy: neat disablement of transforms in pipeline (#7736) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-09-16 23:31:48 +08:00
bhsueh_NV
8226ef23dc
Revert "[None][feat] support attention dp for qwen3 dense model" (#7765) 2025-09-16 19:09:04 +08:00
Kaiyu Xie
6eef19297f
[None] [chore] cherry pick changes on slurm scripts from release/1.1.0rc2 (#7750) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-09-16 16:07:13 +08:00
Li Min
b278d06481
[TRTLLM-6898][feat] Add Cute DSL nvfp4 linear op (#7632) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-09-16 14:25:26 +08:00
Bo Li
3f4e160cba
[None][chore] Fix error when running trtllm-bench without cuda graph. (#7725) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-09-15 20:30:23 -07:00
Void
103b554734
[None][fix] Ensure that the W4A8 custom input scale remains aligned across all ranks (#7614) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-09-16 11:04:26 +08:00
Yanchao Lu
e5cead1eb9
[TRTLLM-6295][test] Exit as early as possible and propagate exit status correctly for multi-node testing (#7739) 
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-09-16 09:59:18 +08:00
xiweny
c076a02b38
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Signed-off-by: Daniel Stokes <dastokes@nvidia.com>
Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: xiweny <13230610+VALLIS-NERIA@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Daniel Stokes <dastokes@nvidia.com>
Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-09-16 09:56:18 +08:00
Necofish
96f11b10ae
[None][feat] support attention dp for qwen3 dense model (#7618) 
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
 2025-09-16 09:33:22 +08:00
Ziyi Xiong
536e8776cd
[TRTLLM-6668][feat] Enable overlap scheduler for two-model spec decoding (#7651) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-09-16 07:33:44 +08:00
Izzy Putterman
8097be7e9c
[None][feat] Eagle, use last hidden post norm (#7546) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-09-15 12:23:57 -04:00
jmydurant
7deefb3d2b
[TRTLLM-7192][feat] optimize MLA chunked prefill && support fp8 mla chunked prefill (#7477) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-09-15 21:43:49 +08:00
Zheng Duan
24fc1f9acf
[None][fix] using arrival time in llmapi when creating LlmRequest in pytorch workflow (#7553) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-09-15 07:26:01 -04:00
Wanli Jiang
e080294725
[TRTLLM-7918][feat] Revert "Support kvcache reuse for phi4mm (#7563)" (#7722) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-09-15 17:19:44 +08:00
Wanli Jiang
fc9f4c9295
[TRTLLM-7918][feat] Support kvcache reuse for phi4mm (#7563) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-09-15 15:47:00 +08:00
DylanChen-NV
d5df0af017
[https://nvbugs/5467981][fix] Fix Qwen2.5-VL fails with cuda graph padding (#7122) 
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
 2025-09-15 15:02:34 +08:00
Chang Liu
47e37755a3
[TRTLLM-6903][feat] Support chunked prefill for multimodal models (#6843) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-09-14 20:10:10 -07:00
Pengyun Lin
c2bc39af63
[TRTLLM-1302][feat] Topk logprobs for TRT backend and top1 logprob for PyT backend (#6097) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-09-12 15:32:34 +08:00
Chang Liu
3a9847eb84
[https://nvbugs/5498165][fix] fix permission error for config file lock (#7656) 
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-09-11 10:36:51 +08:00
Dom Brown
fc9d426589
[https://nvbugs/5505402] [fix] Disable deep_gemm for Qwen3 QKNormRoPEAttention and Linear layers due to accuracy issues (#7616) 
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-09-10 18:30:48 +01:00
Leslie Fang
d219a4f225
[None][chore] remove executor config in kv cache creator (#7526) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-10 21:14:44 +08:00
Yiqing Yan
76c5e1a12f
[None][infra] Bump version to 1.1.0rc5 (#7668) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-09-10 16:06:54 +08:00
Kanghwan
758c22f832
[#7208][fix] Fix config type of MedusaConfig (#7320) 
Signed-off-by: Kanghwan Jang <861393+karljang@users.noreply.github.com>
 2025-09-09 23:25:17 -07:00
Frida Hou
bbb5ae3349
[#5861][autodeploy] Refactor: Quantization Transforms with Inheritance (#7227) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-09-10 13:00:06 +08:00
Zheyu Fu
c353ff342e
[None][feat] Make the should_use_spec_decode logic a bit smarter (#7112) 
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
 2025-09-10 12:53:59 +08:00
Chang Liu
faa2f46554
[TRTLLM-5059][feat] Enable KV-cache reuse and add E2E tests for llava-next (#7349) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-09-09 14:51:36 -04:00
Jin Li
d49374bc45
[TRTLLM-7408][feat] Wrap MOE with custom op. (#7277) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-09-09 12:18:56 -04:00
Richard Huo
dcd110cfac
[None][chore] add TorchLlmArgs to the connector api (#7493) 
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
 2025-09-09 09:05:59 -04:00
NVJiangShao
cc7593987b
[https://nvbugs/5434424][fix] A quick fix for the wrong output issue of SM89 blocked scaling batched GEMM when the input tensor is non-contiguous. (#7615) 
Signed-off-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
 2025-09-09 08:58:15 -04:00
tomeras91
6e712dd1cc
[None][fix] enable NvFP4/FP8 quantization for Nemotron-H architecture (#7589) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-09-09 11:42:22 +03:00
Linda
9cb5410067
[https://nvbugs/5454559][fix] handle bias term in fuse_gate_mlp (#7449) 
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
 2025-09-09 10:26:17 +02:00
William Zhang
c53d1814a7
[None][feat] Extend VLM factory and add Mistral3 factory (#7583) 
This commit:

* extends existing factory interfaces to enable Mistral3 in AutoDeploy.
* adds a Mistral3 VLM factory.
* adds various model patches for pixtral (the vision model) and mistral3
  to make the VLM export compliant.
* adjusts checkpoint loading code to take possible parameter name
  conversions into account.
* fixes a sampling bug (the `end_id` needs to be take into account when
  sampling, but it is not included in the stop words' token IDs).

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-09-09 02:47:18 -04:00
Guoming Zhang
f53fb4c803 [TRTLLM-5930][doc] 1.0 Documentation. (#6696) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-09 12:16:03 +08:00
zhanghaotong
96af324ff1
[None][fix] Add try-catch in stream generator (#7467) 
Signed-off-by: Zhang Haotong <zhanghaotong.zht@antgroup.com>
Co-authored-by: Zhang Haotong <zhanghaotong.zht@antgroup.com>
 2025-09-08 16:09:26 -04:00
Chuang Zhu
77657a1c12
[TRTLLM-7361][feat] KV cache transfer for uneven pp (#7117) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-09-08 13:37:46 -04:00
Leslie Fang
3e0073e86b
[None][chore] remove executor config in instantiate sampler (#7516) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-08 09:02:40 -07:00
Eran Geva
5f2a42b3df
[TRTLLM-6142][feat] AutoDeploy: set torch recompile_limit based on cuda_graph_batch_sizes and refactored (#7219) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-09-08 08:45:58 -04:00
Chang Liu
4a1e13897f
[None][feat] Update multimodal utility get_num_tokens_per_image for better generalization (#7544) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-09-08 07:42:46 -04:00
dominicshanshan
c9dca69e1b
[None][chore] Mass integration of release/1.0 - 3rd (#7519) 
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
Signed-off-by: Pamela <179191831+pamelap-nvidia@users.noreply.github.com>
Signed-off-by: Hui Gao <huig@nvidia.com>
Signed-off-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Co-authored-by: Nave Assaf <55059536+Naveassaf@users.noreply.github.com>
Co-authored-by: Yechan Kim <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Co-authored-by: yifeizhang-c <219273404+yifeizhang-c@users.noreply.github.com>
Co-authored-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
Co-authored-by: Erin <14718778+hchings@users.noreply.github.com>
Co-authored-by: chenfeiz0326 <chenfeiz@nvidia.com>
Co-authored-by: ChristinaZ <83400082+ChristinaZ@users.noreply.github.com>
Co-authored-by: Venky <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
Co-authored-by: HuiGao-NV <huig@nvidia.com>
Co-authored-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: Shi Xiaowei <39303645+Shixiaowei02@users.noreply.github.com>
Co-authored-by: Michal Guzek <moraxu@users.noreply.github.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
Co-authored-by: Guoming Zhang <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Co-authored-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Linda <57756729+Linda-Stadter@users.noreply.github.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Jiagan Cheng <jiaganc@nvidia.com>
Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
Co-authored-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-09-08 14:03:04 +08:00
JunyiXu-nv
504bb7ffa9
[TRTLLM-7779][feat] Support multiple postprocess workers for chat completions API (#7508) 
Signed-off-by: Junyi Xu 
Co-authored-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-09-08 11:11:35 +08:00
Yan Chunwei
205c3a144c
[None][chore] expose tokens_per_block into KvCacheConfig (#5911) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-09-07 21:14:10 -04:00
Netanel Haber
0fee8cd028
[TRTLLM-7153] [feat] Move stop_criteria to sample_async (#7041) 
Signed-off-by: Netanel Haber <nhaber@nvidia.com>
 2025-09-07 17:36:49 +03:00
Raayan Dhar
bae9560e62
[https://nvbugs/5448767][fix] sync termination of requests across PP ranks (#7455) 
Signed-off-by: raayandhar <rdhar@nvidia.com>
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-09-07 08:45:49 -04:00
Mike Iovine
45390402fc
[https://nvbugs/5502352][fix] Fix 2-model CDL path (#7543) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-09-06 23:53:27 -04:00
Chang Liu
99b98f1374
[TRTLLM-7440][fix] Split fused_input_embed to separate out host sync (#7280) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-09-06 23:11:39 -04:00
Chang Liu
23500b55c3
[TRTLLM-7398][feat] Support KV cache salting for secure KV cache reuse (#7106) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-09-06 17:58:32 -04:00
QI JUN
12ecb864c2
[None][chore] share input_ids buffers among different cuda graphs (#7236) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-09-06 17:49:42 -04:00
Anthony Chang
12c66f7610
[None][fix] DeepSeek-R1 W4A8 weight loading issue; fixes regression from #6200 (#7123) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-09-07 00:04:56 +08:00
Lucas Liebenwein
74105a45d9
[#6120][feat] AutoDeploy: flexible args for sequence interface + AD multi-modal input processor + llama4 VLM example (#7221) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-09-05 22:10:48 -04:00
Leslie Fang
9eb3911470
[None][chore] Remove executor_config in create_py_executor_instance (#7463) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-05 20:56:03 +08:00
Robin Kobus
a95d9616ba
[#6186][feat] Introduce QKNormRoPEAttention module (#6830) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-09-05 14:04:41 +02:00
Jin Li
2189a2f3ff
[https://nvbugs/5483615][fix] Remove unnecessary assertion to let mai… (#7441) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-09-05 10:56:21 +08:00
Naveenraj Kamalakannan
58d1036bb1
[#3325][feat] Add MCTS and TOT tree-based inference controllers to Scaffolding (#7490) 
Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
 2025-09-04 19:46:49 -07:00
Shunkangz
bddf183e15
[None][feat] Add Request specific exception (#6931) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-09-04 18:43:42 -04:00
Rashid Kaleem
89889fb526
[https://nvbugs/5369366] [fix] Report failing requests (#7060) 
Signed-off-by: Rashid Kaleem <4079439+arekay@users.noreply.github.com>
 2025-09-04 12:56:23 -07:00
Chang Liu
08a0e06621
[TRTLLM-7410][feat] Support hashing and KV cache reuse for videos (#7360) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-09-04 14:39:23 -04:00
sychen52
98a1bffb7c
[OMNIML-2336][feat] Add NVFP4 x FP8 (#6809) 
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
 2025-09-04 09:03:38 -07:00
Enwei Zhu
1745102e72
[TRTLLM-7027][feat] Fuse d2t to logitsBitmaskKernel and fix a race condition in one-model spec (#7481) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-09-04 23:30:14 +08:00
Izzy Putterman
26b133f3a7
[None][feat] MultiLayer Eagle (#7234) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-09-04 10:49:13 -04:00
Wanli Jiang
4e3dded64d
[TRTLLM-6308][feat] Support Aggregate mode for phi4-mm (#7521) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-09-04 20:16:10 +08:00
WeiHaocheng
5bcda7520b
[https://nvbugs/5477730][fix] Fix the alltoall case when tp_size larger than ep_size (#7331) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-09-04 08:10:03 -04:00
kris1025
cce9556858
[https://nvbugs/5485886][fix] Fix resource free of Eagle3ResourceManager (#7437) 
Signed-off-by: linquanh <linquanh@nvidia.com>
 2025-09-04 17:38:13 +08:00
Yiqing Yan
ced5512ae4
[None][chore] Bump version to 1.1.0rc4 (#7525) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-09-04 16:30:47 +08:00
jianweiwu
7090b286b2
[None][fix] fix hunyuan_moe init bug (#7502) 
Signed-off-by: sorenwu <sorenwu@tencent.com>
 2025-09-04 03:06:00 -04:00
Grzegorz Kwasniewski
3755f8ab7d
[TRTLLM-6342][fix] Fixed triggering BMM sharding (#7389) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-09-04 02:01:27 -04:00
William Zhang
a117e7a57e
[TRTLLM-7442][model] Remove unnecessary D2H copies (#7273) 
* Why?

Initial profiling showed there were multiple D2H / H2D copies being
scheduled in the mistral 3.1 small model.

* What?

This commit removes those unnecessary copies by returning `image_sizes`
as a simple list instead of a tensor.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-09-03 23:14:20 -04:00
Jin Li
2a2dfe273b
[https://nvbugs/5485102][fix] Correctly set stride for piecewise outp… (#7442) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-09-04 10:48:15 +08:00
Frida Hou
51a2b8729e
[#7222][autodeploy] Separate run_shape_prop as another graph utility (#7313) 
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-09-03 19:32:50 -04:00
Leslie Fang
bd9ba97d89
[None][chore] Remove two unused parameters in create_py_executor (#7458) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-04 07:31:31 +08:00
Enwei Zhu
5ff3a65b23
[TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) (#6948) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-09-03 15:16:11 -07:00
Mike Iovine
64e3bfa054
[None][fix] Fix KV cache recompute in draft_target spec decode (#7348) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-09-03 15:04:14 -04:00
Anurag Mukkara
ae5136831f
[https://nvbugs/5472947][fix] wait on isend handles before reusing buffers (#7462) 
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
 2025-09-03 13:20:02 +05:30
YueWeng
9a4f60687f
[https://nvbugs/5480289][fix] release slot manager in mtp MTPHiddenStatesManager (#7340) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-09-02 19:37:51 -07:00
Jinyang Yuan
572551b586
[None][perf] Autotune TRT-LLM Gen MoE when using CUDA graphs (#7285) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-09-03 10:08:59 +08:00
Leslie Fang
42697ea32a
[None][chore] rm executor config in kv cache connector (#7372) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-03 08:13:13 +08:00
JunyiXu-nv
eefe5f2093
[TRTLLM-7208][feat] Implement basic functionalities for Responses API (#7341) 
Signed-off-by: Junyi Xu <junyix@nvidia.com>
 2025-09-02 07:08:22 -04:00
tomeras91
9c8d2161d0
[None][doc] fix example in docstring (#7410) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-09-02 11:59:49 +03:00
Leslie Fang
e81c50dbd2
[None][chore] Use llm args in create_py_executor (#7239) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-09-01 16:27:55 -07:00
Mike Iovine
b3c57a7042
[TRTLLM-7353][feat] Implement capturable drafting loops for speculation (#7100) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-09-01 14:37:44 -04:00
QI JUN
ed4087a295 [https://nvbugs/5374016][fix] improve error message (#6893) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Aurelien Chartier
93e623b455 [https://nvbugs/5449155][fix] Fix DeepSeek R1 weight loading for TP16 (#6913) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Liao Lanyu
704fca4178 [TRTLLM-6835][fix] Fix potential hang caused by python multiprocessing when prefetching weights (#6927) 
Signed-off-by: Lance Liao <108499334+lancelly@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Mike Iovine
de55763f13 [https://nvbugs/5455836][fix] Fix llama 4 FP4 (#6911) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
brb-nv
0253036a4e [None][chore] Add docs for Gemma3 VLMs (#6880) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Yukun He
e106045fda [None][fix] Complete the last missing allreduce op in Llama3/4. (#6850) 
The allreduce op of the last decoder layer is missing in some circumstances for the models Llama3 and Llama4.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Anurag Mukkara
b821883b25 [None][fix] Revert phi4-mm aggregate mode (#6907) 
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
2ez4bz
cf0c47ca2d [None][fix] Fix batching bug in Mistral3 model (#6841) 
Prior to this commit, if multiple requests with images were in the same
batch, the batching logic for the images would fail.

This commit fixes it, and adds unit tests for it that were verified to
fail prior to the fix.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
2ez4bz
2480aedb73 [TRTLLM-5252][feat] Add fp8 support for Mistral Small 3.1 (#6731) 
This commit adds some level of FP8 support to Mistral Small 3.1 by:

* disabling quantization for the vision sub-model since `modelopt` does
  support quantizing it (yet).
* extending existing accuracy tests to use a modelopt produced FP8
  checkpoint.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-09-01 11:02:31 +08:00
Tian Zheng
e257cb3533
[None][feat] Support NVFP4 KV Cache (#6244) 
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2025-09-01 09:24:52 +08:00
Zongfei Jing
a7ed26dd8b
[TRTLLM-6747][feat] Merge add sparse exp and shared exp into local reduction (#7369) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-08-31 21:20:00 -04:00
Yiqing Yan
ec595a8e29
[None][chore] Bump version to 1.1.0rc2 (#7394) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-08-31 10:20:38 +08:00
Zhongdongming Dai
9bb0c9500e
[None][docs] Update Dynasor paper info (#7137) 
Signed-off-by: Zhongdongming Dai <zhongdongmin@nvidia.com>
 2025-08-29 18:47:47 -07:00
Fanrong Li
37a1bd810f
[https://nvbugs/5481385][fix] Fix max_seq_len in cuda graph warmup and intermediate_size in fused_moe_deepgemm (#7345) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
 2025-08-29 17:00:43 +08:00
Chang Liu
31b0f0fb0c
[https://nvbugs/5445466][fix] Eliminate race when loading HF dynamic modules (#7268) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-08-29 12:36:30 +08:00
Richard Huo
ce580ce4f5
[None][feat] KV Cache Connector API (#7228) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
 2025-08-28 23:09:27 -04:00
Shiyu Li
b093d94d34
[https://nvbugs/5445466][fix] Bypass MLP TP split for MNNVL in DeepSeek V3 to avoid hanging. (#6886) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-08-28 15:17:48 -07:00
dongfengy
367ff88a5e
[None][feat] Refactor llama4 for multimodal encoder IFB (#6844) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2025-08-28 13:22:19 -07:00
Nikita Korobov
a419b77fb5
[None][fix] mxfp4 padding bug for TRT-LLM and CUTLASS MoE backends (#7214) 
Signed-off-by: Nikita Korobov <14355239+nekorobov@users.noreply.github.com>
 2025-08-28 10:08:05 -07:00
Zongfei Jing
53163bf1df
[TRTLLM-6876][feat] Add low precision all2all for mnnvl (#7155) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-08-28 18:26:16 +08:00
Pengyun Lin
c1e7fb9042
[TRTLLM-7207][feat] Chat completions API for gpt-oss (#7261) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-08-28 10:22:06 +08:00
Mike Iovine
8b216135f0
[None][refactor] Move draft token padding out of Drafter (#7134) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-08-27 11:07:50 +02:00
dongxuy04
abdb2735be
[None][fix] Fix possible hang issue in WideEP and move some tests to pre-merge (#7262) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-08-27 01:39:24 -04:00
Yukun He
bed5bc9f2e
[None][chore] Wrap the swiglu into custom op to avoid redundant device copy. (#7021) 
A redundant D2D copy is observed when enabling torch.compile for the Llama model due to the swiglu triton kernel, which brings perf overhead. Use a custom op to wrap the swiglu op to avoid this overhead.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-08-27 13:02:10 +08:00
Iman Tabrizian
bc84758626
[None][feat] Add logging for OAI disagg server (#7232) 2025-08-26 21:02:03 -07:00
Shunkangz
ff4047414b
[None][opt] Balance the request based on number of tokens in AttentionDP (#7183) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-08-27 11:16:12 +08:00
Fanrong Li
e12868bc00
[None][fix] Remove and fuse some element-wise ops in the ds-r1-fp8 model (#7238) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-08-27 10:35:38 +08:00
Jin Li
028235404b
[TRTLLM-6633][feat] Padding for piecewise cudagraph (#6750) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-08-26 18:31:33 -04:00
Fridah-nv
0f947c64cb
[None][doc] Update autodeploy README.md, deprecate lm_eval in examples folder (#7233) 
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-08-26 10:47:57 -07:00
Frank
78ecfbb4a4
[None][fix] Fix data type of KV Cache percentage in bench. (#7230) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-08-26 12:28:09 -04:00
Void
040f4c70d3
[None][perf] Accelerate global scale calculations for deepEP fp4 combine (#7126) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-08-27 00:13:13 +08:00
Zheng Duan
cf50ba2980
[TRTLLM-6549][feat] add perf metrics endpoint to openai server and openai disagg server (#6985) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-08-26 15:34:44 +08:00
qixiang-99
b165f8bc97
fix/improve kvcache allocation in PyTorch runtime (#5933) 
Signed-off-by: qixiang-99 <203170375+qixiang-99@users.noreply.github.com>
 2025-08-26 12:40:22 +08:00
William Zhang
92576488d3
[None][feat] Skip prefetching consolidated safetensors when appropriate (#7013) 
* Why?

Some models (e.g. anything produced by Mistral) can have both sharded
safetensors and a consolidated safetensor in the same checkpoint
directory. In such cases, prefetching both to memory is a waste of time,
and memory.

* What?

This commit skips over consolidated safetensors when they are not the
only safetensor file present in the checkpoint directory

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-08-25 23:56:21 -04:00
Leslie Fang
20922b7d1f
[None][chore] Create PyExecutor from TorchLlmArgs Part 1 (#7105) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-08-26 10:42:01 +08:00
Grzegorz Kwasniewski
2101d46d68
[TRTLLM-6342][feat] TP Sharding read from the model config (#6972) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-08-25 15:41:27 -07:00
Lucas Liebenwein
97d550b4ba
[None] [AutoDeploy] canonicalize_graph before shape prop for consistent state_dict (#7223) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-08-25 16:59:57 -04:00
Bo Li
bf1b958f1a
[TRTLLM-7319][perf] Fuse slicing into MoE. (#6728) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Sergey Klevtsov <sklevtsov@nvidia.com>
Co-authored-by: Sergey Klevtsov <sklevtsov@nvidia.com>
 2025-08-25 16:52:30 -04:00
Daniel Cámpora
e8e7e52892
[None][chore] Refactored the handle logits pp communication (#7154) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-08-25 16:14:08 -04:00
Frank
788fc62d23
[None][fix] Update to pull LLM from a central location. (#6458) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-08-25 13:07:29 -07:00
QI JUN
bea5e07fb7
[None][refactor] refactor the CUDA graph runner to manage all CUDA graphs (#6846) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-08-25 20:52:05 +08:00
shaharmor98
b32e00e9fd
[None][chore] remove CLI support for mamba cache dtype setting (#7119) 
Signed-off-by: Shahar Mor <17088876+shaharmor98@users.noreply.github.com>
 2025-08-25 08:08:51 -04:00
amitz-nv
a1e03af0f4
[TRTLLM-7346][fix] Improve performance of PyTorchModelEngine._get_lora_params_from_requests (#7033) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-08-25 10:37:40 +03:00
Enwei Zhu
be6d92f09f
[None][fix] Fix MoE load balancer config loading (#7150) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-08-25 01:42:54 -04:00
Yukun He
9c5b464fe0
[None][feat] Apply AutoTuner to fp8_block_scale_deep_gemm to trigger JIT ahead of time. (#7113) 
Because deep_gemm.gp8_gemm_nt will trigger many JIT processes during the inference phase, we need to sweep these shapes ahead of time. Apply the AutoTuner framework to achieve this and retain the potential capability to tune the swap_ab flag.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-08-25 10:48:31 +08:00
ajrasane
068056677f
[None][chore] Enable auto deploy accuracy test in CI (#7179) 
Signed-off-by: ajrasane <131806219+ajrasane@users.noreply.github.com>
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-08-24 08:42:30 -07:00
dongxuy04
19a0ea363b
[TRTLLM-6743][feat] Optimize and refactor alltoall in WideEP (#6973) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
Signed-off-by: Dongxu Yang <dongxuy@nvidia.com>
Co-authored-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-08-24 08:15:29 -04:00
amitz-nv
35e0ae484a
[https://nvbugs/5467232][fix] Fix load_torch_hf_lora to override lora_config.trtllm_modules_to_hf_modules with default only when it has no value (#7132) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-08-24 15:00:24 +03:00
Grace Ho
3d54a1a521
[None] [feat] nsys profile output kernel classifier (#7020) 
Signed-off-by: Grace Ho <grho@nvidia.com>
 2025-08-23 00:57:37 -04:00
Frank
81fd468fec
[None][fix] Correct KV cache percentage report out. (#7102) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-08-22 10:28:57 -07:00
Izzy Putterman
b36460d7b5
[None][feat] Deepseek: Start Eagle work (#6210) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
Co-authored-by: Mike Iovine <miovine@nvidia.com>
 2025-08-22 12:57:17 -04:00
tomeras91
c232ba8157
[TRTLLM-4921][feat] Enable chunked prefill for Nemotron-H (#6334) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
Signed-off-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-08-22 12:15:20 -04:00
Suyog Gupta
e3de5758a3
[#7136][feat] trtllm-serve + autodeploy integration (#7141) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-08-22 08:30:53 -07:00
Yiqing Yan
907bc22fcb
[None][chore] Bump version to 1.1.0rc2 (#7167) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-08-22 22:02:28 +08:00
Daniel Cámpora
099f081e03
[TRTLLM-7155][feat] Unify sampler handle logits implementation. (#6867) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-08-22 08:09:30 +02:00
Yukun He
983dd7e57c
[None][fix] Fix mm_placholder_counts extraction issue. (#7118) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-08-22 12:28:30 +08:00
Wanli Jiang
07c711eb1f
[TRTLLM-6825][fix] Update lora for phi4-mm (#6817) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-08-21 22:00:04 -04:00
dominicshanshan
6f245ec78b
[None][chore] Mass integration of release/1.0 (#6864) 
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: ruodil <200874449+ruodil@users.noreply.github.com>
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: raayandhar <rdhar@nvidia.com>
Co-authored-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
Co-authored-by: ruodil <200874449+ruodil@users.noreply.github.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
Co-authored-by: Bo Deng <deemod@nvidia.com>
Co-authored-by: Guoming Zhang <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Yechan Kim <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: 2ez4bz <133824995+2ez4bz@users.noreply.github.com>
Co-authored-by: Raayan Dhar <58057652+raayandhar@users.noreply.github.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-08-22 09:25:15 +08:00
Daniel Stokes
f7c597ec40
[None][perf] Make finalize fusion part of the tactic selection logic (#6915) 
Signed-off-by: djns99 <40156487+djns99@users.noreply.github.com>
 2025-08-21 14:08:03 -07:00
Fridah-nv
e18dacc931
[#4403][refactor] Move fusion, kvcache, and compile to modular inference optimizer (#7057) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Co-authored-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
 2025-08-21 10:30:36 -07:00
ChristinaZ
c7269ea93a
[https://nvbugs/5392414] [fix] Add customized default routing method (#6818) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-08-21 16:58:41 +08:00
Fridah-nv
647a52698a
[https://nvbugs/5443039][fix] Fix AutoDeploy pattern matcher for torch 2.8 (#7076) 
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-08-21 01:14:51 -04:00
Chang Liu
75b8a90816
[None][fix] Fix llama4 multimodal by skipping request validation (#6957) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-08-20 21:58:53 -04:00
Yechan Kim
0893afae3d
[TRTLLM-6771][feat] Support MMMU for multimodal models (#6828) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-08-21 08:54:12 +08:00
Robin Kobus
b95cab2a7c
[None][ci] move unittests to sub-directories (#6635) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-08-20 05:42:22 -04:00
Chang Liu
ce53832610
[TRTLLM-7326][feat] Add standalone multimodal encoder (#6743) 
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-08-19 21:42:50 -07:00
Fridah-nv
c02592d051
[None][autodeploy] Add group attention pattern for solar-pro-preview (#7054) 
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
 2025-08-19 18:57:09 -04:00
Jinyang Yuan
0e30fe4372
[None][fix] Fix assertion errors of quantization when using online EPLB (#6922) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-08-19 11:28:36 -07:00
Michal Guzek
7334f9390c
[None][fix] Accommodate Phi3/4 to work with ModelOpt's FP8 ckpts in Torch (#6761) 
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
 2025-08-19 09:22:46 -07:00
zhhuang-nv
7e135d2ea7
[None][feat] Use Separate QKV Input Layout for Context MLA (#6538) 
Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
 2025-08-19 22:04:48 +08:00
Zero Zeng
953f4fd69e
[None][fix] acceptance rate calculation fix in benchmark_serving (#6746) 
Signed-off-by: Zero Zeng <38289304+zerollzeng@users.noreply.github.com>
 2025-08-19 17:29:36 +08:00
Shunkangz
54ec2c1af1
[None][opt] Add batch wait timeout in fetching requests (#6923) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-08-19 03:50:08 -04:00
Yi Zhang
a15af879ec
[None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic (#6615) 
Signed-off-by: yizhang-nv <187001205+yizhang-nv@users.noreply.github.com>
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2025-08-19 09:58:44 +08:00
Daniel Cámpora
d16af87d03
[TRTLLM-7158][feat] Introduce sampler options in trtllm bench (#6855) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-08-18 18:10:05 -04:00
Kaiyu Xie
e88cb92f24
[None] [feat] Support accurate device iter time (#6906) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-08-18 13:47:14 +08:00
bhsueh_NV
85cbd0263b
[None][feat] Support Yarn on Qwen3 (#6785) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-08-17 07:21:29 +08:00
Izzy Putterman
f6ff0e3311
[None][fix] Skip Topk if 0 (#6934) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-08-16 02:17:36 -04:00
Daniel Cámpora
53312eeebd
[TRTLLM-7157][feat] BREAKING CHANGE Introduce sampler_type, detect sampler according to options (#6831) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-08-16 00:27:24 -04:00
Yiqing Yan
ec3d9f8052
[None][chore] Bump version to 1.1.0rc1 (#6953) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-08-16 10:32:47 +08:00
Yuening Li
1f8ae2b2db
[TRTLLM-5863][feat] Support MoE INT8 Weight-Only-Quantization in PyTorch Workflow (#6629) 
Signed-off-by: Yuening Li <62227368+yueningl@users.noreply.github.com>
 2025-08-15 17:15:49 -04:00
dongfengy
0ad0b967bb
[None][fix] Make TP working for Triton MOE (in additional to EP we are using) (#6722) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2025-08-15 16:58:42 -04:00
ajrasane
4162d2d746
[None][test] Add accuracy evaluation for AutoDeploy (#6764) 
Signed-off-by: ajrasane <131806219+ajrasane@users.noreply.github.com>
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-08-15 13:46:09 -04:00
yifeizhang-c
4127d77678
[https://nvbugs/5394392][fix] Enlarge scheduler capacity under disagg bs == 1 (#6537) 
Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
 2025-08-15 09:52:06 -07:00
liji-nv
18ccd053d3
[https://nvbugs/5427801][fix] Torch compile support for Llama4 and Ea… (#6858) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-08-15 11:14:20 -04:00
tomeras91
f7dbc1435a
[None] [chore] Mamba cache in separate file (#6796) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-08-15 13:42:51 +03:00
Bo Li
15aabc1540
[None][fix] Fix perfect router. (#6797) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-08-14 20:09:08 -07:00
Frank
2cc59aacb3
[None][fix] Correct reporting of torch_dtype for ModelConfig class. (#6800) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-08-14 22:46:20 -04:00
qianbiao
5c2f0fd03d
[None] [feat] Add Tencent HunYuanMoEV1 model support (#5521) 
Signed-off-by: sorenwu <sorenwu@tencent.com>
Co-authored-by: sorenwu <sorenwu@tencent.com>
Co-authored-by: bhsueh_NV <11360707+byshiue@users.noreply.github.com>
 2025-08-15 06:56:44 +08:00
Mike Iovine
078e907b16
[https://nvbugs/5455651][fix] Make ngram use XQA attention on Blackwell (#6873) 
Signed-off-by: Michael Iovine <miovine@nvidia.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: Mike Iovine <mike.iovine7@gmail.com>
 2025-08-14 18:36:19 -04:00
Bo Li
26f413ad90
[https://nvbugs/5450262][fix] Fix unsupported alltoall use case (#6882) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-08-14 17:46:54 -04:00
Matthias Jouanneaux
69574ad730
[TRTLLM-5966][feat] Helix: extend mapping to support different CP types (#6816) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
 2025-08-14 09:00:02 -07:00
kris1025
4aed7a7d19
[TRTLLM-6853][feat] refactor deepseekv3 model (#6698) 
Signed-off-by: linquanh <linquanh@nvidia.com>
 2025-08-14 11:03:17 -04:00
Pengbo Wang @ NVIDIA
ffc976ceaf
[https://nvbugs/5445466][fix] fix deepseek r1 hang by not enabling mnnvl by default (#6860) 
Signed-off-by: Pengbo Wang <221450789+pengbowang-nv@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
 2025-08-14 22:36:56 +08:00
Shi Xiaowei
1095dfd03c
[None][fix] BREAKING CHANGE: Mismatch between docs and actual commands (#6323) 2025-08-14 03:48:57 -04:00
Yan Chunwei
0132c1db84
[https://nvbugs/5427043][fix] request length exceeds max_num_tokens (#6821) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-08-14 13:31:12 +08:00
Bo Deng
d8acca495b
[TRTLLM-6675][infra] Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/6623 (#6735) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
 2025-08-14 04:36:38 +00:00
jmydurant
4200fa46d1
[None][feat] Add support for Hopper MLA chunked prefill (#6655) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-08-14 10:39:26 +08:00
Izzy Putterman
ef53de8eef
[None][feat] Add test for speculative rejection sampler (2-model) (#6542) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-08-13 22:09:35 -04:00
Tin-Yin Lai
6c52bb07ff
[https://nvbugs/5302040][feat] Add whisper support (Bert Attention on SM100 and GPTAttention for cross attention on SM100) (#5527) 
Signed-off-by: tinyinl <tinyinl@nvidia.com>
 2025-08-13 11:19:13 -07:00
danielafrimi
bda42f8c3a
[None][feat] Support running heterogeneous model execution for Nemotron-H (#6866) 
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
 2025-08-13 19:51:19 +03:00
Anthony Chang
2198587b35
[https://nvbugs/5378031] [feat] Hopper W4A8 MoE supports ModelOpt ckpt for PyT backend (#6200) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-08-13 21:24:40 +08:00
Yukun He
bc5f766e0e
[TRTLLM-4501][feat] AutoTuner tuning config refactor and valid tactic generalization. (#6545) 
* Generalize the definition of tactics so that users can implement more customizable tactic types, making the configurations clearer for each kernel run. 
* Allow the user not to specify the `gen_tuning_buckets` or the `map_to_tuning_buckets` function.
* Other code refactoring.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-08-13 16:25:22 +08:00
Void
1d80df0955
[None][feat] DeepEP LL combine FP4 (#6822) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-08-13 04:20:21 -04:00
Mike Iovine
f68e03e646
[https://nvbugs/5452167][fix] Fix ngram padding issue (#6837) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-08-13 11:23:16 +08:00
Yechan Kim
12102e2d48
[TRTLLM-6772][feat] Multimodal benchmark_serving support (#6622) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-08-12 19:34:02 -07:00
Fanrong Li
1bbc0e323b
[None][fix] Pre-allocate workspaces for DeepGEMM MoE to avoid frequent cudaFree/cudaMalloc (#6811) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-08-13 10:27:57 +08:00
rakib-hasan
2923eb88a1
[None][fix] Refactoring input prep to allow out-of-tree models (#6497) 
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
 2025-08-12 20:29:10 -04:00