kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-06 03:01:50 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,931 Commits 28 Branches 67 Tags 2 GiB
ccdd8461ac
Commit Graph

257 Commits

Author SHA1 Message Date
Frida Hou
7910d4d2a9
[#8242][feat] Add int4 GPTQ support for AutoDeploy (#8248) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2026-01-30 23:07:24 -08:00
Karthik
5a97374f3c
[#9525][feat] add L2 norm pattern matcher and fusion transform (#10767) 
Signed-off-by: Karthik Vetrivel <kvetrivel@nvidia.com>
 2026-01-30 16:05:53 -05:00
nvyocox
4af47208d8
[None][feat] Export ONNX for DriveOS LLM (#10117) 
Signed-off-by: yocox <yocox@nvidia.com>
 2026-01-30 15:43:11 -05:00
Chenghao Zhang
e033929221
[None][feat] AutoDeploy: Flashinfer kernels bringup (#10867) 
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
 2026-01-29 14:59:29 -08:00
Anish Shanbhag
24ac86c485
[https://nvbugs/5761391][fix] Include triton-kernels as a packaged dependency (#10471) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2026-01-28 19:56:32 -08:00
Frida Hou
f03908cf9e
[None][fix] fix Qwen2/3 export for AutoDeploy (#11007) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2026-01-28 16:53:21 -08:00
Bala Marimuthu
393c3d259e
[#10245][feat] AutoDeploy: Add Minimax M2 support (#10525) 
Signed-off-by: Balamurugan Marimuthu <246387390+bmarimuthu-nv@users.noreply.github.com>
 2026-01-28 17:22:32 -05:00
gramnarayan
744a955cbb
[None][chore] AutoDeploy: Eagle One-Model [1/n]: PyTorch impl for Eagle3 Llama checkpoint (#10674) 
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2026-01-28 12:10:49 -08:00
Lucas Liebenwein
ff3a494f5c
[#10013][feat] AutoDeploy: native cache manager integration (#10635) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-27 11:23:22 -05:00
sunnyqgg
ff0dd6076e
[TRTLLM-10062][feat] Enable MTP for Nemotron Super (#10754) 
Signed-off-by: qgai <qgai@nvidia.com>
 2026-01-26 11:23:26 -05:00
Lucas Liebenwein
00f341be49
[#8982][feat] AutoDeploy attention dp support (#10728) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-26 09:43:33 -05:00
Taylor Yeonbok Lee
1fbbb1f3cd
[None][feat] AutoDeploy: Enhance memory consumption for MoE fusion transform (#10772) 
Signed-off-by: Taylor Yeonbok Lee <249374542+taylor-yb-lee@users.noreply.github.com>
 2026-01-23 15:22:54 -08:00
William Zhang
2146c23786
[#9306][refactor] Refactor AutoDeployConfig into LlmArgs (#10613) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2026-01-22 16:02:49 -05:00
Grzegorz Kwasniewski
d8e6e22060
[https://nvbugs/5819002][fix] fix sharding tests (#10775) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-22 20:02:48 +01:00
tcherckez-nvidia
128d4ac5be
[None][chore] NVFP4 MoE - Move weights transformation to fusion phase… (#10803) 
Signed-off-by: Tal Cherckez <tcherckez@nvl72070-T11.cm.cluster>
Signed-off-by: Tal Cherckez <tcherckez@nvl72039-T03.cm.cluster>
Signed-off-by: Tal Cherckez <tcherckez@nvl72098-T11.cm.cluster>
Signed-off-by: tcherckez-nvidia <127761168+tcherckez-nvidia@users.noreply.github.com>
Co-authored-by: Tal Cherckez <tcherckez@nvl72070-T11.cm.cluster>
Co-authored-by: Tal Cherckez <tcherckez@nvl72039-T03.cm.cluster>
Co-authored-by: Tal Cherckez <tcherckez@nvl72098-T11.cm.cluster>
 2026-01-22 13:08:05 +02:00
tcherckez-nvidia
6e72aff866
[#10838][fix] Add missing dist strategy param. fix typo for ad_logger… (#10892) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2026-01-22 10:38:31 +02:00
Taylor Yeonbok Lee
895bb94b3d
[#8241][feat] Support model_kwargs for pytorch backend (#10351) 
Signed-off-by: Taylor Yeonbok Lee <249374542+taylor-yb-lee@users.noreply.github.com>
 2026-01-21 20:51:38 -08:00
Grzegorz Kwasniewski
eb326073d8
[TRTLLM-10785][feat] Fix sharding dashboard errors (#10786) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-20 09:25:36 +01:00
Lucas Liebenwein
9879400479
[#10642][feat] AutoDeploy: optimized canonicalize_graph utilities [1/2] (#10675) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-18 13:42:30 -05:00
Eran Geva
4d2916d683
[#10688][fix] AutoDeploy Fix CUDA graph batch sizes exceeding max_batch_size (#10687) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-18 13:31:01 -05:00
Eran Geva
a11f0dbd61
[#10696][fix] AutoDeploy prevent torch.export from specializing batch dimension when max_batch_size=1 (#10697) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-18 10:42:49 +02:00
Grzegorz Kwasniewski
7bf4dd9f63
[TRTLLM-10318][feat] Fixing Nemotron sharding: support for sharding buffers (#10319) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Signed-off-by: Lucas <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: Grzegorz Kwasniewski <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Lucas <11156568+lucaslie@users.noreply.github.com>
 2026-01-17 04:02:06 -05:00
Chenghao Zhang
0b748d5bba
[None][chore] update flashinfer to 0.6.0 (#10522) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2026-01-16 16:22:06 -05:00
Chenghao Zhang
b6acd96616
[None][fix] AutoDeploy: Fix the nvfp4 fused_moe (#10727) 
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
 2026-01-16 12:04:40 -08:00
Lucas Liebenwein
49c6f73554
[None][bug] AutoDeploy: fix regression in kv cache resize memory estimation (#10726) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-16 09:52:03 +08:00
Anish Shanbhag
faa80e73fd
[None][feat] Auto download speculative models from HF for pytorch backend, add speculative_model field alias (#10099) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2026-01-14 21:06:07 -08:00
HuiGao-NV
b10704428d
[https://nvbugs/5787566][fix] Only keep a limited number of performance statistic data (#10569) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2026-01-14 07:53:01 -05:00
Yuxian Qiu
39cefd6125
[None][refactor] Unify the usage of MPIDist and TorchDist. (#10380) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-14 14:05:47 +08:00
Frida Hou
bf16fbd86c
[#9283][feat] AutoDeploy: separate rms pattern detection from fusion (#9969) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2026-01-13 14:57:27 -05:00
Neta Zmora
7b7f1e2ba1
[None][feat] AutoDeploy: refactor memory usage logging (#8505) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Signed-off-by: Gal Hubara-Agam <96368689+galagam@users.noreply.github.com>
Co-authored-by: Gal Hubara-Agam <96368689+galagam@users.noreply.github.com>
 2026-01-13 21:03:09 +02:00
Eran Geva
489dd60312
[#10513][fix] AutoDeploy: removed self.mlp_type leftovers from last moe refactor (#10512) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-08 14:49:40 -05:00
Eran Geva
6511dbaea0
[#10417][fix] AutoDepoloy - Reverted to direct computation of minusA (#10509) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-08 13:43:41 +02:00
tcherckez-nvidia
7e88212d24
[None][bug] fix export for microsoft/Phi-3-medium-128k-instruct (#10455) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2026-01-07 10:30:24 +02:00
Lucas Liebenwein
bb6a3973aa
[https://nvbugs/5732942][fix] AutoDeploy: handle transformers 4.57.1 upgrade fixes (#10466) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-06 19:55:49 -05:00
Karthik
617f728903
[#8460][feat] Revive and simplify Model Explorer visualization integration (#10150) 
Signed-off-by: Karthik Vetrivel <kvetrivel@nvidia.com>
 2026-01-05 22:15:25 -05:00
Karthik
4e50cb5708
[#10170][fix] Add export patch for GraniteMoe MoE models to enable torch.export compatibility (#10169) 
Signed-off-by: Karthik Vetrivel <kvetrivel@nvidia.com>
 2026-01-05 16:13:45 -05:00
Grzegorz Kwasniewski
ea380ff45c
[TRTLLM-9767][feat] Fixed recursive node traversals (#10379) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-05 18:42:06 +02:00
Eran Geva
3749a2ce1c
[#10374][fix] fixed race condition in AutoDeploy's mp tests port acquisition (#10366) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2026-01-05 13:33:01 +02:00
Yukun He
d272f1a9bc
[TRTLLM-8821][feat] Apply AutoTuner to AllReduce Op for strategy tuning. (#8531) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-05 15:44:37 +08:00
Grzegorz Kwasniewski
0d1f5ad7a2
[TRTLLM-10358][feat] Added proper rescaling of FP4 weights (#10378) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-03 16:26:16 -05:00
Gal Hubara-Agam
f3dd6da080
[#10056][chore] AutoDeploy: Enable Nemo SuperV3 accuracy test (#10308) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-01-02 11:20:19 +02:00
Gal Hubara-Agam
5845951538
[#10056][fix] AutoDeploy: Handle deletion of nested params in sharding (#10376) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-01-01 08:11:11 -05:00
tcherckez-nvidia
4868772ad7
[None][feat] Add export data to build and run script for AD (#10299) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2026-01-01 04:54:47 -05:00
Lucas Liebenwein
1bbe71b3ed
[#10244][feat] AutoDeploy: separate prefill/decode in flashinfer (#10252) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-12-31 17:01:24 -05:00
tcherckez-nvidia
464847c6be
[#9717][chore] Standardize MoE weights interface (#10295) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2025-12-31 07:37:18 -05:00
Eran Geva
74832a1895
[https://nvbugs/5766986][fix] fixed the shard_all_unprocessed default value to align with the default.yml (#10271) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-30 08:54:13 -05:00
Neta Zmora
966231d29c
[#9626][feat] Add an auto-deploy transform for using cutlass FP4 MoE kernels (#10304) 
Add a transform to relace torch.ops.auto_deploy.torch_quant_nvfp4_moe
with the optimized torch.ops.auto_deploy.trtllm_quant_nvfp4_moe_fused.

Currently generates the wrong results when the number of rows in MoE FC1 weights is not divisible by 128,
so torch.ops.auto_deploy.trtllm_quant_nvfp4_moe_fused is not set as the default FP4 MoE implementation (i.e. the transform is disabled).

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-29 23:18:15 +02:00
Neta Zmora
f3f02315df
[None][chore]: small refactoring to auto-deploy MoE operator (#10300) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-25 12:27:11 -05:00
gramnarayan
a9eb5afc9f
[#9241][feat] AutoDeploy: Support Eagle3 Speculative Decoding (#9869) 
Support two model flow with no overlap scheduler or chain drafter. Drafting model is in PyTorch backend.

Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2025-12-24 23:30:42 -05:00
Neta Zmora
c4b36d31ff
[#10137][feat] AutoDeploy FP8 MoE refactor (#10138) 
The trtllm (cutlass) fp8 moe operator performs W3+W1 fusion (concat) during inference and we want to move this fusion to the model optimization time.

The Cutlass MoE kernel is used thru a trtllm torch operator.
Its implementation uses two FC operations (fc1 and fc2) while the canonical MoE API defines three GEMM operations and their associated weights (W1, W2, W3) so when we switch from the torch.moe op to the trtllm.moe op we also change terminology from w1, w2, w3 to fc1, fc2.

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-12-24 18:58:10 +02:00