kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-06 11:11:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
4,899 Commits 28 Branches 67 Tags 2 GiB
5ff244ce54
Commit Graph

166 Commits

Author SHA1 Message Date
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
Lucas Liebenwein
a4880ffdbb
[None][fix] AutoDeploy: remove mem check for a log unit test (#11120) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-29 15:41:51 -05:00
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
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
Grzegorz Kwasniewski
38bcee189c
[TRTLLM-10362][feat] Added Mamba and MLA layers to the sharding tests (#10364) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Signed-off-by: Grzegorz Kwasniewski <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-01-28 10:34:10 +01:00
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
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
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
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
Frida Hou
069ad68d3c
[None][fix] AutoDeploy: skip mxfp4_moe test unless on Hopper (#10729) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2026-01-16 16:24:37 -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
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
Lucas Liebenwein
15b43e8a14
[https://nvbugs/5777041][fix] fix AutoDeploy ep sharding test (#10460) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-14 21:53:56 -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
Chenghao Zhang
38f249b479
[https://nvbugs/5548861][fix] AutoDeploy: Fix the test (#10521) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2026-01-09 13:30:24 -08:00
Lucas Liebenwein
30f8455d29
[https://nvbugs/5747878][fix] unwaive llama4 scout tests (#10468) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-07 23:33:45 -05:00
Lucas Liebenwein
d736c7f290
[https://nvbugs/5761665][fix] AutoDeploy: handle bugs for 25.12 dlfw upgrade (#10511) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-07 20:16:53 -05:00
Lucas Liebenwein
6095c80e56
[https://nvbugs/5721907][fix] AutoDeploy: improve numerical stability of flashinfer attention test (#10467) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-01-06 21:11:06 -05:00
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
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
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
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
tcherckez-nvidia
12e1cb8d7e
[#9717][chore] Refactor MoE code to use enums (#9910) 
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
 2025-12-22 15:14:56 -05:00
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
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
Chenghao Zhang
22c6e8a424
[None][fix] Autodeploy: fix some legacy flashinfer attention test errors (#9928) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-17 12:27:22 -08:00
Eran Geva
ce7a42f4cf
[https://nvbugs/5731717][fix] fixed flashinfer build race condition during test (#9983) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-12-15 20:30:24 -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
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
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
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
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
Frank
f6df9eb2a6
[TRTLLM-9089][chore] Port prepare_dataset into trtllm-bench (#9250) 2025-12-08 10:37:40 -08:00
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
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
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
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
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
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
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