kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-06 19:21:52 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,611 Commits 28 Branches 67 Tags 2 GiB
bf16fbd86c
Commit Graph

1428 Commits

Author SHA1 Message Date
Bo Li
a66eeab537
[TRTLLM-9805][feat] Skip Softmax Attention. (#9821) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2025-12-21 02:52:42 -05:00
Enwei Zhu
21a93fbf9d
[TRTLLM-9992][perf] Enable PDL for CuteDSL kernels and overlap MoeOutputMemset (#10043) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-20 03:12:41 -05:00
Yuxian Qiu
e75331480f
[None][fix] fix draft_lengths for CUDA graph capture. (#10004) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-20 09:04:48 +08:00
Ziyi Xiong
70b4d282c6
[TRTLLM-7736][feat] Incrementally update the inputs of target and draft models (#9708) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-19 15:11:25 +08:00
William Zhang
478b6b20a1
[#9230][refactor] Replace nemotron patches with custom model implementation (#9751) 
[#9230][refactor] Replace nemotron patches with custom model implementation

* Why?

Patching for nemotron H models was growing out of hand, and made certain
optimizations more complex than they needed to be.

* What?

This commit finally gets rid of them, and replaces them with the custom
model implementation in `modeling_nemotron_h.py`.

Closes #9230
Closes NvBug 5747867

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-12-18 19:36:27 -08:00
Wangjue Yao
9f283f330b
[None][feat] Support Mooncake transfer engine as a cache transceiver backend (#8309) 
Signed-off-by: wjueyao <wyao123@terpmail.umd.edu>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-12-19 10:09:51 +08:00
Enwei Zhu
6fe89ea00f
[TRTLLM-9819][perf] Reuse alltoall workspace for CuteDSL MoE output (#9840) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-18 10:36:38 -08:00
CarstyYou
0b279f4ad4
[https://nvbugs/5456493][feat] Add fp8 bmm on sm120 (#9687) 
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
 2025-12-18 22:57:20 +08:00
ZhichenJiang
4e55b83101
[None][perf] Add more optimization options for MOE CuteDSL finalized kernel (#10042) 
Signed-off-by: zhichen jiang <zhichenj@NVIDIA.com>
 2025-12-18 22:49:28 +08:00
Lucas Liebenwein
76ec820465
[#7532][feat] AutoDeploy: gather logits before lm head (#9962) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-17 19:50:13 -08:00
Yuan Tong
f7e245668b
[TRTLLM-9680][perf] Optimize TRTLLMSampler log_probs performance (Core fix has been merged via #9353) (#9655) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-12-17 17:56:01 +08:00
Yukun He
00c0564334
[None][chore] Remove unnecessary warning log for tuning. (#10077) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 01:51:17 -08:00
Yukun He
18b335d584
[TRTLLM-9989][fix] Disable tvm_ffi for CuteDSL nvFP4 dense GEMM. (#10040) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 00:41:26 -08:00
Yukun He
2fd1a23e4c
[TRTLLM-9998][fix] Change trtllm-gen MoE distributed tuning strategy back to INDEPENDENT (#10036) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-17 00:35:22 -08:00
Void
47404196fa
[None][fix] Enabled simultaneous support for low-precision combine and MTP. (#9091) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-12-17 13:37:08 +08:00
Aurelien Chartier
7175d89b48
[None][fix] Fix iteration stats for spec-dec (#9855) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-12-16 14:11:38 -08:00
ruodil
07f307d131 [https://nvbugs/5652552][fix] cherry-pick add printing for llm args (#9206) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-16 13:33:20 -05:00
Enwei Zhu
609d1d0383
[None][fix] Fix Illegal Memory Access for CuteDSL Grouped GEMM (#10008) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-16 04:06:49 -08:00
Wanli Jiang
8af51211c1
[FMDL-1222][feat] Support weight and weight_scale padding for NVFP4 MoE cutlass (#9358) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-16 12:41:17 +08:00
Yechan Kim
8ba8699f66
[TRTLLM-8310][feat] Add Qwen3-VL-MoE (#9689) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-12-15 20:05:20 -08:00
ChristinaZ
dff77efa2a
[None][feat] Add routing support for the new model for both cutlass and trtllm moe backend (#9792) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-12-15 19:59:08 -08:00
Michal Guzek
e6187d8109
[https://nvbugs/5708810][fix] Fix TRTLLMSampler (#9710) 
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
 2025-12-15 23:26:52 +01:00
Faraz
0c31502fbc
[None][feat] disable fused gemm for sm121 (#9916) 
Signed-off-by: list <58580514+farazkh80@users.noreply.github.com>
 2025-12-15 12:07:06 -05:00
Yukun He
9e7182b603
[TRTLLM-9615][feat] Implement a distributed tuning system (#9621) 
Four distinct strategies are implemented to accommodate different distributed tuning scenarios, including BROADCAST, INDEPENDENT, MERGE, PARALLEL.

* Distributed tuning is disabled by default, with the INDEPENDENT strategy as the fallback. This conservative approach prevents unexpected behavior in standard use cases.
* Only operations with significant tuning time overhead have been assigned the PARALLEL strategy, which allows the same tensor parallelism (TP) rank to tune tactics concurrently across different ranks. This targeted approach balances performance gains with stability.
* Operations with nested tuning structures, such as NVFP4GemmUnifiedRunner, currently support only the INDEPENDENT strategy. This restriction exists because the synchronization mechanism is optimized only for leaf operations and doesn't yet handle nested hierarchies.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-15 21:08:53 +08:00
Grzegorz Kwasniewski
83885c69e7
[TRTLLM-9136][feat] 2D parallel EP TP support (#9459) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-12-15 09:52:29 +01:00
Yuxian Qiu
7588029763
[None][feat] Async pp send for PPCommTorch. (#9976) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-15 14:03:46 +08:00
Ziyi Xiong
f2aee0db03
[TRTLLM-9854][feat] Optimize the host overhead of _sample_async (#9935) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-15 13:28:54 +08:00
Fanrong Li
8f144d9282
[TRTLLM-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-15 12:42:25 +08:00
xxi
f5696df285
[TRTLLM-8961][feat] ConfigurableMoE support DeepGemm (#9858) 2025-12-15 10:47:15 +08:00
Zongfei Jing
bf923a1074
[None] [chore] Comments cleanup (#9978) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-12-15 09:46:37 +08:00
Yuxian Qiu
fcda1a1442
[None][fix] disable async pp send for ray cases. (#9959) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-13 20:22:36 -08:00
nvxuanyuc
a5a37227d6
[None][feat] Fused kernels (qknormrope + moe routing) and two-model MTP support for glm4moe (#9852) 
Signed-off-by: Xuanyu Chen <xuanyuc@nvidia.com>
 2025-12-14 10:47:24 +08:00
Mike Iovine
383b13e0e5
[None][feat] Implement sampling on 1-model EAGLE3 (#9885) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-13 07:38:22 -08:00
jellysnack
079ef8ae77
[None][feat] Graceful Error Handling for Guided Decoder (#9078) 
Signed-off-by: jellysnack <oleg.jellysnack@gmail.com>
Signed-off-by: jellysnack <158609015+jellysnack@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-13 19:57:59 +08:00
Balaram Buddharaju
6a6e41f802
[TRTLLM-9468][chore] Update disagg benchmarking scripts to support context parallelism (#9720) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-12 22:29:41 -08:00
bhsueh_NV
e49c70f6df
[None][feat] Support Mistral Large3 LLM part (#9820) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-12-13 11:44:27 +08:00
Faraz
98d72c7648
[None][feat] spark cublas LUT table for llama-8b-bf16 perf (#9811) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2025-12-12 22:37:56 -05:00
Balaram Buddharaju
461446045e
[TRTLLM-9493][feat] Add helixPostProcessNative kernel for cp_dim=2 (#9924) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-12 16:49:25 -08:00
Yuxian Qiu
cd4e639536
[None][feat] Async pp send. (#9952) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-13 00:52:30 +08:00
Yihan Wang
9df4dad3b6
[None][fix] Introduce inline namespace to avoid symbol collision (#9541) 
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
 2025-12-12 23:32:15 +08:00
Balaram Buddharaju
af315d8ef1
[TRTLLM-5972][chore] Load balance decode token KV cache with helix parallelism (#9757) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-12 22:29:05 +08:00
Lucas Liebenwein
e767fc649a
[None][feat] AutoDeploy: prepare_metadata revisited (#9764) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-12 20:14:14 +08:00
jthomson04
4f6d4da035
[None][perf] Fix TPOT when min_tokens set (#9862) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2025-12-11 13:55:31 -08:00
Erin
89dabf5aa1
[TRTLLM-9736][feat] AsyncLLM and verl integ (#9353) 
Signed-off-by: Liwei Ma <liweim@nvidia.com>
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-authored-by: Liwei Ma <liweim@nvidia.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
Co-authored-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-12-11 09:33:25 -08:00
xxi
488d38f88d
[TRTLLM-8959][feat] ConfigurableMoE support CUTLASS (#9772) 2025-12-12 00:22:13 +08:00
Zongfei Jing
c76b428e2e
[TRTLLM-9685] [feat] Add gather fc1 kernel by cuteDSL (#9618) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-12-11 16:21:32 +08:00
Ziyi Xiong
81222c3670
[None] Fix warning when capturing CUDA graph (#9746) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-10 19:22:38 -08:00
Yukun He
072f236002
[None][fix] Fully resolve the tactic recovery issues in AutoTuner serialized cache (#9835) 
Restrict tactic types to those compatible with AutoTuner cache serialization and deserialization.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-10 20:41:04 +08:00
Yukun He
979f37e443
[None][fix] Fix nvfp4 gemm allowed backends arg passing (#9837) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-09 20:09:53 -08:00
dhansen-nvidia
2d33ae94d5
[https://nvbugs/5508301][feat] Move D->H copies to a worker thread whe… (#8463) 
Signed-off-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
Signed-off-by: dhansen-nvidia <218031328+dhansen-nvidia@users.noreply.github.com>
Co-authored-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
 2025-12-09 18:51:31 -05:00
Mike Iovine
07c76a5fac
[None][feat] Make 2-model spec dec use the 1-model kernels (Hopper) (#8810) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-12-09 11:06:31 -05:00
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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