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
4,357 Commits 25 Branches 59 Tags 2.1 GiB
c059e6caa1
Commit Graph

1892 Commits

Author SHA1 Message Date
Stefan Niebler
d600b9f851
[TRTLLM-6756][feat] Update BeamSearch for TorchSampler (#9660) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-12-09 10:44:01 +01:00
Robin Kobus
76f49c903b
[None][fix] Additional model outputs for pipeline parallelism (#9794) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-12-09 10:41:22 +01:00
Jiagan Cheng
4a3a66b124
[https://nvbugs/5677746][fix] Use first PP rank's schedule result in other PP ranks to fix PP hang (#9659) 
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
 2025-12-08 18:43:52 -08:00
bhsueh_NV
d6f961d3fe
[None][feat] Add llama4 scaling (#9771) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-12-09 10:27:39 +08:00
Chenghao Zhang
75f5446d67
[#9753][feat] AutoDeploy: Implement add rms_norm fusion (#9754) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-08 14:24:27 -08:00
Jhao-Ting Chen
da074be037
[None][fix] Fix #8383 introduced TRTLLM backend python error (#9804) 
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
 2025-12-08 13:31:37 -08:00
Eran Geva
23cf72b0f8
[#8921][feat] Added symetric memory AllReduce strategy (#8919) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-08 13:12:56 -08:00
Thor Johnsen
f9380581c5
[https://nvbugs/5508267][fix] Proper handling of inactive canceled requests (#9280) 
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
 2025-12-08 13:11:44 -08:00
Jhao-Ting Chen
0a09465089
[https://nvbugs/5567586][feat] Ampere xqa swa specdec for GPT-OSS Eagle3-one-model (#8383) 
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
 2025-12-08 11:16:05 -08:00
Frank
f6df9eb2a6
[TRTLLM-9089][chore] Port prepare_dataset into trtllm-bench (#9250) 2025-12-08 10:37:40 -08:00
sunnyqgg
1c7b7cdd47
[TRTLLM-9506][fix] Fix AR for DeepSeek-R1 2 model path (#9661) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-12-08 10:12:32 -05:00
Eran Geva
98db262a67
[None][fix] Switch AutoDeploy's default allreduce strategy to NCCL (#9666) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-08 03:26:21 -08:00
Guoming Zhang
448bb1a44f
[TRTLLM-9431][perf] Enable multistream for Linear Attention in Qwen3-… (#9696) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-12-08 13:39:12 +08:00
Li Min
a422d70be6
[None][chore] Enable tvm_ffi for cute dsl nvfp4_gemm to reduce host overhead. (#9690) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-12-08 13:28:11 +08:00
Yukun He
8b9ab9a701
[None][fix] Fix two tuning cache miss issues. (#9743) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-08 10:47:21 +08:00
xxi
8e27ce7084
[TRTLLM-9603][feat] Enable ConfigurableMoE test in the CI (#9645) 2025-12-08 10:19:40 +08:00
Ludwig Schneider
41ce14ab04
[None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314) 
Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>
 2025-12-07 09:43:26 -08:00
JunyiXu-nv
b210f22c7e
[https://nvbugs/5703953][fix] Preserving ip:port for trtllm-serve before initializing llm (#9646) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-06 20:13:48 -08:00
Yan Chunwei
e4c707845f
[None][fix] enable hmac in RPC (#9745) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-12-07 08:24:46 +08:00
Jonas Li
2645a78f34
[TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature (#9682) 
Signed-off-by: Jonas Li <6110159+longlee0622@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-12-06 02:24:51 -08:00
mpikulski
8d2178d321
[TRTLLM-9522][chore] implement default attach_multimodal_embeddings (#9664) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-12-05 22:12:16 -08:00
Enwei Zhu
7cd5a67e25
[TRTLLM-9372][feat] Enable CuteDSL MoE with Large EP (#9592) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-05 22:08:52 -08:00
xxi
c2f2add6df
[None][fix] fix a bug: deepseek_fp8_block_scales in TRTLLMGEN-MoE use 2D x_sf instead of 1D (#9658) 
Signed-off-by: xxi <xxi@nvidia.com>
 2025-12-05 21:01:39 -08:00
shuyixiong
df5b32966d
[None][fix] Fix triton moe load_weight (#9649) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-12-06 11:17:04 +08:00
QI JUN
0915c4e3a1 [TRTLLM-9086][doc] Clean up TODOs in documentation (#9292) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-05 17:50:12 -05:00
Chenghao Zhang
d6f95a4363
[None][feat] AutoDeploy: Perf optimization for Attention and rmsnorm (#9719) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-05 12:59:04 -08:00
Robin Kobus
eb0b426e5d
[None][refactor] Improve request processing function in sampler (#9671) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-12-05 16:41:49 +01:00
Robin Kobus
faf682b8bc
[TRTLLM-7136][feat] Update load_weights method to include mapping parameter in checkpoint loaders (#9583) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-12-05 16:07:20 +01:00
gramnarayan
74df9b180b
[#9602][feat] AutoDeploy: Support TRTLLM Sampler (#9641) 
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2025-12-04 19:24:11 -08:00
Lizhi Zhou
0d0a16fff4
[TRTLLM-8920][feat] decouple disagg service from fastapi (#8714) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-12-05 10:44:16 +08:00
Aurelien Chartier
041bb32151
[None][fix] Fix TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS for MTP/EAGLE (#9608) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-12-04 08:23:57 -08:00
Anthony Chang
60cdca3740
[None][fix] Recover TRTLLM MoE Perf for DEP (#9562) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-12-04 22:10:25 +08:00
Jin Li
e5d4305c04
[https://nvbugs/5467531][fix] Unwaive fused_moe all to all test with … (#9617) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-04 18:17:24 +08:00
tcherckez-nvidia
f9aa86dbdd
[#8733][feat] Add Llama4 MoE handling to AutoDeploy (#9556) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
Signed-off-by: tcherckez-nvidia <127761168+tcherckez-nvidia@users.noreply.github.com>
Co-authored-by: Neta Zmora <nzmora@nvidia.com>
 2025-12-04 08:03:33 +02:00
JunyiXu-nv
6d2daec5d0
[TRTLLM-8274][feat] Check if executor is shutdown in /health entrypoint (#9057) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-04 13:49:40 +08:00
Tailing Yuan
4eed648e22
[None][feat] Add weights initialization and context phase parser to layer-wise benchmarks (#9667) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-12-04 13:41:15 +08:00
Jin Li
87e0c8a749
[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSeekV3 (#7838) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-04 13:32:11 +08:00
Necofish
323a82f4d5
[None][fix] fix error when processing batches containing both text and mm data (#8381) 
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
 2025-12-04 14:28:24 +09:00
mpikulski
744f0eff1b
[TRTLLM-9522][fix] restore trtllm-serve mm_embedding_serve (#9669) 2025-12-03 19:27:11 -08:00
Wanli Jiang
4485e516a2
[None][feat] Update Qwen3CodeToolParser to align tool-calling parameters (#9540) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-04 06:47:32 +08:00
gramnarayan
098b9ff226
[#9147][feat] AutoDeploy: Draft Target Speculative Decoding (#9275) 
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2025-12-04 05:13:49 +08:00
Lucas Liebenwein
a1964bcbbc
[#9643][fix] AutoDeploy: fix nano sharding config (#9668) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-04 03:10:25 +08:00
Wei-Ming Chen
d9fba85396
[OMNIML-2932] [feat] nvfp4 awq support (#8698) 
Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>
 2025-12-03 19:47:13 +02:00
Gal Hubara-Agam
d7bd62b1a0
[https://nvbugs/5693853][fix] Fix error handling when querying machin… (#9483) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2025-12-03 19:44:51 +02:00
Guoming Zhang
b5e2b9b51f
[https://nvbugs/5702795][fix] Remove the warning message for aten.log. (#9665) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-12-04 00:02:15 +08:00
Iman Tabrizian
09beaa5933
[None][fix] Fix wide ep MoE error (#9642) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-12-03 23:11:06 +08:00
Michal Guzek
4e5b10da48
[https://nvbugs/5552132][fix] Enable LoRa for GPT OSS Torch (#8253) 
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
 2025-12-03 15:42:15 +01:00
Perkz Zheng
992781dc7b
[None][feat] update trtllm-gen nvfp4 kernels with better performance (#9510) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
 2025-12-03 21:35:49 +08:00
JunyiXu-nv
743486b2ea
[TRTLLM-6842][feat] Support Response API for general purpose (#9392) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-03 16:49:26 +08:00
Pengyun Lin
1d4fb89235
[TRTLLM-8241][feat] Aliasing to comply to LlmArgs (#9586) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-03 15:28:45 +08:00
Bo Li
8b5ededc83
[TRTLLM-9391][chore] Automatically estimate required workspace. (#9535) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-03 12:49:38 +08:00
Suyog Gupta
93871d52b2
[None][chore] AutoDeploy update cuda stream manager for multi-device (#9575) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-12-02 20:43:14 -08:00
heyuhhh
a08eb81cce
[None][feat] Add RocketKV usage doc and e2e accuracy test on LongBenchV2 (#9572) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2025-12-03 11:33:46 +08:00
Anurag Mukkara
642dfae73a
[https://nvbugs/5698434][fix] Use separate weight mapper for draft (#9607) 
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
 2025-12-02 16:00:22 -08:00
Enwei Zhu
a3455f55c7
[None][chore] Fix trtllm-eval and move GroupedGemmInputsHelper (#9612) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-03 07:55:03 +08:00
Chang Liu
3916d032ec
[None][chore] Remove traceback dump for multimodal input processor (#9634) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-12-03 07:41:03 +08:00
Grzegorz Kwasniewski
0a7a88e74e
[TRTLLM-8946][feat] Improved heuristics to detect shardable regions (#9200) 
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: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-02 22:08:19 +01:00
Neta Zmora
a560ba5546
[#9550][feat] AutoDeploy: Add NVFP4 Cutlass MoE kernels (#9551) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-03 01:39:38 +08:00
Shi Xiaowei
227d42e492
[https://nvbugs/5651854][fix] Fix dist-serving perf by clearing CPU affinity (#9549) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2025-12-03 01:17:03 +08:00
Lucas Liebenwein
e72ce98c0f
[#9150][feat] AutoDeploy: reviewer comments for #9150 (#9527) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-02 12:09:10 -05:00
William Zhang
2dd3ebf037
[#9150][feat] Add code for nano v3 to custom implementation in AD (#9465) 
* Why?

We would like to show an alternative to monkey-patching in AutoDeploy.

* What?

This commit builds on the existing custom model implementation for
NemotronH and adds the bits relevant for MoE layers.

Part of #9150.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-12-02 08:56:44 -08:00
Thor Johnsen
95049eea86
[https://nvbugs/5627710][fix] Fix synchronization bugs in KvCacheTransferManager that can cause corrupted blocks (#9056) 
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
Co-authored-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-12-02 09:10:21 -06:00
Yan Chunwei
b86256eb54
[TRTLLM-9144][fix] enhance RPC robustness (#8711) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-12-02 21:37:59 +08:00
Jin Li
21e3dc11d8
[https://nvbugs/5667774][fix] Refine Piecewise Cuda Graph Condition for DP (#9393) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-02 21:09:15 +08:00
brb-nv
be48cdf1d1
[TRTLLM-9466][test] Evaluate helix parallelism with DSV3 Lite (#9597) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-02 20:10:07 +08:00
mpikulski
84a1531594
[TRTLLM-9488][feat] use FlashInfer.sampling by default (#9545) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-12-02 16:29:55 +08:00
shuyixiong
1a2118b8fe
[https://nvbugs/5702793][fix] Fix uncontiguous tensor view (#9576) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-12-02 15:41:32 +08:00
Wanli Jiang
5657a00ec0
[FMDL-1328][feat] Add support for nano-v3 and super-v3 with pytorch backend (#9261) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-02 13:40:20 +08:00
Guoming Zhang
6fbe87c8b5
[None][chroe] Polish qwen3-next modeling code. (#8902) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-12-02 11:28:35 +08:00
Iman Tabrizian
356a52edf5
[None][feat] Add support for KVCache reuse for DSv32 (#9383) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-12-02 11:14:30 +08:00
Shijie
dcf5c86720
[None][feat] Unify nvfp4 gemm backend (#8963) 
Signed-off-by: Shijie Wang <jaywan@nvidia.com>
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Shijie <jaywan@nvidia.com>
Co-authored-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-02 11:03:51 +08:00
Yuening Li
09c840184c
[None][fix] Prevent YAML partial kv_cache_config from incorrectly overriding the complete kv_cache_config (#9262) 
Signed-off-by: Yuening Li <62227368+Yuening-wa@users.noreply.github.com>
 2025-12-02 10:10:08 +08:00
Eran Geva
c9771ebb99
[#9198][feat] Refactor dist ops in AutoDeploy (#9301) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-02 02:36:32 +08:00
Chenghao Zhang
0a2104dce9
[None][feat] AutoDeploy: Use the router gemm op for nemotron MOE (#9500) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-01 10:24:31 -08:00
Venky
639c939a4f
[TRTC-1943][feat] Env vars override support in LLM API (#9104) 
Signed-off-by: Venky Ganesh <23023424+venkywonka@users.noreply.github.com>
 2025-12-01 10:04:49 -08:00
brb-nv
f61067cbb5
[None][chore] Defer exposing context parallel configs (#9552) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-01 09:50:02 -08:00
Stefan Niebler
f155812eb0
[TRTLLM-6756][feat] Add Beam Search to TorchSampler (#8509) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-12-01 18:48:04 +01:00
Enwei Zhu
90345ad3f3
[None][fix] Skip Allreduce init for Attention DP (#9542) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-01 21:24:40 +08:00
alel
4107254c82
[TRTLLM-6222][feat] Several perf opt for cuteDSL nvf4 gemm (#9428) 
Signed-off-by: Yuhan Li <51736452+liyuhannnnn@users.noreply.github.com>
 2025-12-01 18:10:45 +08:00
Yukun He
730eb3d859
[None][fix] Replace hash method with unique_id for cutedsl MoE runners. (#9569) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-01 17:02:33 +08:00
Neta Zmora
bc25fff039
[#9496][fix] AutoDeploy: remove auto-tuner from nvfp4_gemm forward (#9497) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-01 10:04:39 +02:00
Fanrong Li
d69bf9f92a
[None][feat] add chat template kwargs support to longbench-v2 (#9544) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-01 15:59:13 +08:00
Gaoji Liu
9d2df04a72
[None][doc] fix mtp.py typo (#9307) 
Signed-off-by: liugaoji <757394026@qq.com>
 2025-11-30 21:55:13 -08:00
Li Min
1797e91dfd
[TRTLLM-6222][feat] Extend cute_dsl_nvfp4_gemm to sm103. (#9543) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-12-01 10:19:36 +08:00
Enwei Zhu
34e2fa5c96
[https://nvbugs/5690172][fix] Fix Qwen3-235B ATP accuracy issue with PDL (#9530) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-01 09:10:21 +08:00
heyuhhh
6e470aab72
[None] [feat] Optimize the algorithm part of RocketKV (#9333) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2025-12-01 09:04:09 +08:00
xxi
c12e67bb66
[TRTLLM-8958][feat] and [TRTLLM-8960]: create ConfigurableMoE and support TRTLLMGenFusedMoE as backend (#9486) 2025-12-01 08:37:07 +08:00
brb-nv
b77f4ffe54
[TRTLLM-5971][feat] Integrate helix parallelism (#9342) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-11-29 15:17:30 -08:00
dominicshanshan
6345074686
[None][chore] Weekly mass integration of release/1.1 -- rebase (#9522) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: qgai <qgai@nvidia.com>
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
Signed-off-by: Simeng Liu <simengl@nvidia.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Vincent Zhang <vinczhang@nvidia.com>
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
Signed-off-by: Michal Guzek <moraxu@users.noreply.github.com>
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Co-authored-by: yunruis <205571022+yunruis@users.noreply.github.com>
Co-authored-by: sunnyqgg <159101675+sunnyqgg@users.noreply.github.com>
Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>
Co-authored-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: JunyiXu-nv <219237550+JunyiXu-nv@users.noreply.github.com>
Co-authored-by: Simeng Liu <109828133+SimengLiu-nv@users.noreply.github.com>
Co-authored-by: Guoming Zhang <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: Vincent Zhang <vcheungyi@163.com>
Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
Co-authored-by: Michal Guzek <moraxu@users.noreply.github.com>
Co-authored-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Co-authored-by: Leslie Fang <leslief@nvidia.com>
Co-authored-by: Shunkangz <182541032+Shunkangz@users.noreply.github.com>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-11-29 21:48:48 +08:00
Grzegorz Kwasniewski
cff54fcae3
[#8948][feat] Support custom sharding config (#9143) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-11-29 05:28:05 +08:00
binghanc
db5b876124
[None][feat] support for more accurate AR calculation (#9323) 
Signed-off-by: binghanc <176802681+binghanc@users.noreply.github.com>
 2025-11-29 00:34:21 +08:00
Matthias Jouanneaux
f8dd494536
[None][perf] Helix: improve all-to-all perf for large CP size (#9494) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
Co-authored-by: Zheyu Fu <zheyuf@nvidia.com>
 2025-11-28 07:24:55 -08:00
mpikulski
e5f39ec7cf
[TRTLLM-9488][feat] add 'disable_flashinfer_sampling' config option (#9454) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-28 13:00:39 +01:00
Robin Kobus
5eae3650c3
[None][fix] Pass checkpoint_format to create_input_processor (#9521) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-28 10:32:29 +01:00
Zhenhuan Chen
7c3bb8534d
[None][chore] Revert "[None][fix] change allreduce workspace dtype to torch.int64 t… (#9538) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2025-11-28 16:45:23 +08:00
Yukun He
60c43a200a
[None][fix] Fix on-disk cache and revise logger/statistics for AutoTuner. (#9211) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-28 13:32:21 +08:00
Lucas Liebenwein
2f8bd6fb36
[#9150][feat] AutoDeploy Nemotron-Flash support (#9504) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-27 18:03:57 +01:00
Enwei Zhu
c2562fc800
[https://nvbugs/5687820][fix] Remove self.abort() in DetokenizedGenerationResult (#9449) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-11-27 22:54:40 +08:00
Bo Li
62b771877c
[TRTLLM-9389][chore] Refactor AlltoallMethodType. (#9388) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-27 21:09:29 +08:00
Fanrong Li
2d5eadf65f
[None][fix] fix TP support for DeepSeek-V3.2 on hopper (#9484) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-27 21:02:25 +08:00
Zhenhuan Chen
e47927e847
[None][fix] change allreduce workspace dtype to torch.int64 to avoid overflow (#9479) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2025-11-27 17:08:41 +08:00
xxi
f1ed057b4c
[cherry-pick][https://nvbugs/5670793][fix] Solve trtllm-serve launch_disaggregated issue (#9346) 
Signed-off-by: xxi <xxi@nvidia.com>
 2025-11-27 16:13:58 +08:00
Ziyi Xiong
1dd55d8507
[https://nvbugs/5698581][fix] Init draft tokens for CUDA graph dummy request (#9505) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-11-27 13:05:37 +08:00
Jiagan Cheng
14762e0287
[None][fix] Replace PYTORCH_CUDA_ALLOC_CONF with PYTORCH_ALLOC_CONF to fix deprecation warning (#9294) 
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
 2025-11-27 12:22:01 +08:00
QI JUN
a67d94963e
[None][chore] update comments in llm_args.py (#9472) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-27 11:06:34 +08:00
Aurelien Chartier
f2f197360d
[#9463][feat] Add revision option to trtllm commands (#9498) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-11-27 09:30:01 +08:00
Chenghao Zhang
18fbda5cdb
[None][feat] AutoDeploy: Add A_log fusion for Mamba layers (#9422) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-26 14:39:20 -08:00
Chenghao Zhang
bc7b60e016
[None][feat] AutoDeploy: Remove redundant copies in mamba layers (#9461) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-26 14:38:33 -08:00
Aurelien Chartier
ef7ee6a940
[None][feat] Add environment variable to force spec-dec number of accepted tokens (#9371) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-11-26 07:22:16 -08:00
Chang Liu
b10137fdd5
[None][feat] Support MLA chunked prefill for DeepSeek V3.2 model (#9376) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-11-26 16:38:25 +08:00
Enwei Zhu
1bf2d750a2
[None][chore] Upgrade CuteDSL to 4.3.0 (#9444) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-11-26 14:53:09 +08:00
JunyiXu-nv
b7308a4000
[https://nvbugs/5580099][fix] Cherry pick IMA issue fix from release/1.1 (#9032) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-11-26 13:09:06 +08:00
shuyixiong
d8acea1db3
[TRTLLM-9293][feat] Enable partial weight loading to support streaming update weights (#9224) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-11-26 10:59:06 +08:00
Yiqing Yan
1b9edf62c9
[None][chore] Bump version to 1.2.0rc5 (#9455) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-11-26 08:37:53 +08:00
Chuang Zhu
0e9c7f8c07
[https://nvbugs/5685143][fix] avoid cudaFree overlap with cuda graph (#9438) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-11-25 16:20:29 -08:00
Suyog Gupta
e484bec82f
[None][chore] AutoDeploy add multi stream moe pass to default.yaml (#9430) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-25 14:16:13 -08:00
Robin Kobus
32f53910ef
[TRTLLM-909][feat] Overlap context chunks in pipeline parallel mode (#9308) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-25 22:11:51 +01:00
Eran Geva
afc52d7b93
[https://nvbugs/5647400] [fix] Enlarged the AllReduce workspace size to 64MB. Added AllReduce strategy to AD config. (#9145) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-11-25 10:56:07 -08:00
mpikulski
899fda9e47
[TRTLLM-9490][feat] use FlashInfer's top_k_sampling_from_probs (#9457) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-25 18:53:53 +01:00
mpikulski
c5f52ab304
[TRTLLM-8376][feat] top-p optimization (removes redundant softmax) (#9411) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-25 18:46:48 +01:00
YueWeng
cc336c4abd
[TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-11-25 09:40:55 -05:00
Pengyun Lin
fa61825c74
[None][feat] Support custom chat template for tool calling (#9297) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-11-25 22:07:04 +08:00
Tailing Yuan
51ef0379d2
[None][feat] Add a parser to layer-wise benchmarks (#9440) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-11-25 05:45:16 -08:00
Fanrong Li
c36f144591
[None][chore] Fix trtllm-eval for PyTorchLLM (#9427) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-25 04:49:03 -08:00
Yueh-Ting (eop) Chen
a38d91aae2
[https://nvbugs/5537996][fix] Let KV cache manager block initialization be aware whether it is doing a dry run or not (#9093) 
Before this commit, the kv cache manager does the same regardless, which causes a mis-calculation in free memory available to allocate for the KV cache manager, hence causing a crash.

This commit fixes this by letting KV cache manager initialization be aware whether it is doing the dry run or not. If it is a dry run, use the max_tokens setting that is already pre-calculated and filled into kv_cache_config.max_tokens.

Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2025-11-25 17:27:11 +08:00
Yukun He
e580da4155
[TRTLLM-7963][feat] Cold L2 cache when doing autotune benchmarking. (#8779) 
The performance results of some kernels could be easily affected by the warm/cold L2 cache status. To achieve more precise profiling results, the L2 cache is cleared for every execution by the circular buffer method for better benchmarking during autotuning.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-25 15:06:22 +08:00
William Zhang
a4049fc557
[#9413][fix] Minor fixes to nemotron H and custom models in AD (#9416) 
* Why?

There were a couple of issues with the recently merged custom model
injection for AutoDeploy + the reference implementation of nemotron
H:
- `d_mlp` was left in despite being mathematically always null (could
  lead to runtime issues during sharding).
- the custom model mapping was inherited by children factories.

* What?

This commit fixes these issues, and refactors the key of the custom
implementation to be based on the name of the configuration class as
well.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-11-24 20:17:33 -08:00
Suyog Gupta
efd503751f
[#9271][perf] Enable multi-stream MOE optimization in AutoDeploy (#9322) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-24 19:50:10 -08:00
Yuxian Qiu
8a0295015f
[None][chore] Reduce nested nvtx ranges. (#9347) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-11-25 09:58:41 +08:00
bhsueh_NV
1a93583438
[None][feat] Support Yarn on QwQ-32B model (#9059) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
Signed-off-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Co-authored-by: NVJiangShao <91270701+StudyingShao@users.noreply.github.com>
 2025-11-25 07:27:28 +08:00
Yibin Li
1ce483c999
[TRTLLM-7967][feat] Adding Starcoder2 PyTorch Backend Support (#8923) 
Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>
 2025-11-24 11:23:22 -08:00
Yukun He
960851f419
[None][chore] Remove unnecessary log in the short tuning profile (#9387) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-24 12:31:26 +08:00
Yukun He
39076410a8
[https://nvbugs/5676748][fix] Fix mismatched nvfp4 gemm sf shape. (#9336) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-24 12:16:32 +08:00
brb-nv
c045e359a7
[https://nvbugs/5637012][fix] Fix helix unit tests (#9369) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-11-23 19:34:22 -08:00
QI JUN
34a6d2d28f
[TRTLLM-9302][chore] Move build config from BaseLlmArgs to TrtLlmArgs (#9249) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-24 10:54:41 +08:00
Yukun He
c3acf965a6
[TRTLLM-7963][fix] Several improvements of autotuning quality (#9348) 
* Skip the shape profile generating process if the profile has already been found in the cache under tuning mode. This is a prerequisite for nested autotuning because host overhead might be included during the profiling of the high-level op.
* Enable the profiling with CUDA graph as the default profiling method.
* Apply a heuristic method to cut off the number of repeat times of profiling according to a few-run time measurement.
 2025-11-24 10:38:45 +08:00
Bo Li
fcfec93cad
[TRTLLM-9389][chore] Rename AlltoAll backend names (#9329) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-23 13:52:57 -08:00
JadoTu
0582e54b61
[None][fix] modify qwen3-next sampling stop_tokens (#9331) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-11-23 21:10:09 +08:00
William Zhang
11a0b276fb
[#9230][feat] Slimmed down implementation of nemotron H (#9235) 
* Why?

The reference nemotron H code on HuggingFace is out of date,
and therefore bugged, and has several untested code paths.
This makes an already hairy patching system even hairier.

The proposal is to do away with those patches, and replace the
original implementation with one that is heavily slimmed down.

* What?

This PR sets the basis for an alternative path with such a 
slimmed down implementation that:
- fixes bugs in the current HF implementation
- adds no new dependencies to TensorRT-LLM
- does away with unnecessary features for TensorRT-LLM/
  AutoDeploy:
- no training related code (dropout, gradient checkpointing, etc.)
- no caching logic (we want to replace it with our own anyway)
- no attention masking where possible
- reuses existing AD custom ops for mamba SSM update /
   causal conv1d / attention

In order for the above to be usable in the AD apparatus,
`AutoModelForCausalLMFactory` is extended to allow registrations
of custom model implementations.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-11-23 03:13:32 -08:00
Neta Zmora
3952a61681
[#9388][fix] AutoDeploy: Fix cutlass BF16 MoE kernel invocation (#9339) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-11-21 17:05:03 -08:00
Chenghao Zhang
564989865c
[TRTLLM-9082][feat] AutoDeploy: Move the moe Align kernel to AOT (#9106) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-21 16:05:48 -08:00
Izzy Putterman
eb7792e875
[None][feat] Eagle: PostNorm and multilayer options (#9233) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-11-21 17:39:00 -05:00
Enwei Zhu
13fbd4366a
[TRTLLM-9370][feat] Integration of CuteDSL NVFP4 grouped GEMM (Part 2: SwiGLU Fusion and Finalize Fusion) (#9288) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-11-21 14:03:38 -08:00
Ziyi Xiong
5df907b388
[https://nvbugs/5590408][fix] Fallback to greedy sampling in two-model overlap scheduler (#9321) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-11-21 10:19:59 -05:00
HuiGao-NV
6dd2fcd7b3
[https://nvbugs/5629833][fix] Don't fill tensors with 0 (#9296) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-11-21 20:50:05 +08:00
mpikulski
cddc7549d1
[TRTLLM-9191][feat] support out-of-tree models in trtllm-serve (#9269) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-21 04:23:47 -08:00
mpikulski
095b6864a8
[TRTLLM-8650][fix] beam search request validation (#8433) (#9228) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-21 04:08:45 -08:00
Yiqing Yan
8cd3b496e9
[None][chore] Bump version to 1.2.0rc4 (#9363) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-11-21 18:28:12 +08:00
xxi
cc0dc7c124
[TRTLLM-8957][feat] create communication related classes (#8968) 2025-11-20 22:32:42 -08:00
Pengyun Lin
eca68e4465 [https://nvbugs/5564465][fix] Overwrite only if default_max_tokens is legal (#8538) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-11-20 12:43:13 -05:00