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
4,128 Commits 25 Branches 59 Tags 2.1 GiB
fd3d3a553d
Commit Graph

1808 Commits

Author SHA1 Message Date
ruodil
82480346aa
[https://nvbugs/5652552][fix] add printing for llm args (#9205) 
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>
 2025-11-17 23:58:36 -08:00
Tri Dao
fc088e642c
[None][feat] Support Glm4MoeForCausalLM (#8256) 
Signed-off-by: Tri Dao <daominhtri0503@gmail.com>
Co-authored-by: Xuanyu Chen <xuanyuc@nvidia.com>
 2025-11-18 09:43:21 +08:00
Lucas Liebenwein
6d0a8edbbb
[None][chore] local imports for AutoDeploy in serve and bench (#9199) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-18 08:14:32 +08:00
Robin Kobus
df41f220a2
[TRTLLM-8831][feat] Enable early exit with overlap scheduler (#8587) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-17 18:07:13 +01:00
Mike Iovine
6151a4c9d6
[None][feat] Add simple optimizations for MTP 2-model (#9176) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-17 10:05:39 -05:00
Kaiyu Xie
04be5a704e
[None] [fix] Fix missing ActivationType issue (#9171) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-11-17 10:43:25 +08:00
Anthony Chang
86cfb3ea7e
[None][feat] Update TRTLLM MoE cubins; reduce mxfp4 weight padding requirement; tighten TMA bound (#9025) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-11-17 10:04:29 +08:00
Jinyang Yuan
6dc70aa0e5
[https://nvbugs/5613089][fix] Fix the rank to access all_rank_chunk_size_list when chunked MoE is used (#8723) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-11-17 10:01:08 +08:00
sunnyqgg
7862b15a65
[TRTLLM-8778][feat] Add tree attention support for blackwell arch (#8975) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-11-17 09:01:53 +08:00
Guoming Zhang
e0f69657c7
[None][fix] Update the attention layers counting for Qwen3-next. (#9072) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-11-16 11:52:56 -08:00
JadoTu
3cde84581d
[None][fix] Make the sliced nvfp4 output contiguous (#9123) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-11-15 20:00:54 +08:00
Chenghao Zhang
f6f6e1f25d
[#9102][feat] AutoDeploy: Support fp8 kv cache (#9107) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-13 23:55:45 -08:00
Lizhi Zhou
8bd779171e
[https://nvbugs/5631254][fix] avoid torch.compile for multiple times (#9135) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-11-13 21:49:52 -08:00
Suyog Gupta
d12cb9436d
[None][feat] Autodeploy add triton configs and optimize mamba prefill (#9083) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-13 19:15:43 -08:00
heyuhhh
f07e9977c6
[None] [feat] Use triton kernels for RocketKV prediction module (#8682) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2025-11-13 18:51:09 -08:00
Tailing Yuan
cc4c980e03
[None][feat] Add Qwen3-Next to layer-wise benchmarks (#9065) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-11-14 10:03:00 +08:00
JunyiXu-nv
fdb0787e85
[None][chore] Support json_schema in response_format (#8934) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-11-14 09:43:13 +08:00
Erin
44d1c75701
[TRTLLM-8988][feat] Unify MPI & Ray's req/response handling with RPC Client/Server (#8765) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-11-13 17:21:24 -08:00
Neta Zmora
34dc6869f3
[#8732][feat] Update TRTLLM Cutlass MoE kernels with ReLU2 (#9011) 
Update TRTLLM Cutlass MoE kernels with ReLU2 activation.

Nemotron-6 requires ReLU2 (i.e. squared ReLU) MoE activation function.
The PR adds this and adds an API to set the activation function, in general.
The ReLU2 changes are based on this FlashInfer PR: https://github.com/flashinfer-ai/flashinfer/pull/1954.

The PR also updates the Auto Deploy MoE backend for 16-bit and FP8 from
Triton (`torch.ops.auto_deploy.triton_moe_fused`, `torch.ops.auto_deploy.triton_quant_fp8_moe`) to TRTLLM/Cutlass (`torch.ops.auto_deploy.trtllm_moe_fused`, `torch.ops.auto_deploy.trtllm_quant_fp8_moe_fused`).

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-13 16:54:45 -08:00
dongxuy04
a370643b26
[None][fix] support topk autotuner input for expert slot per group larger than 32 (#9087) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-11-14 08:37:20 +08:00
Leslie Fang
daa31d78f4
[https://nvbugs/5652552][fix] Log the llm args for main branch (#9120) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-11-14 07:43:21 +08:00
Frida Hou
b51258acdd
[None][autodeploy] fix weight extraction for graph based quantized checkpoints (#9109) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-13 13:14:24 -08:00
Frida Hou
e96a3d294d
[None][autodeploy] minor refactor to rmsnorm transforms (#8657) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-13 13:13:58 -08:00
Jinyang Yuan
12f339f3bf
[None][fix] Fix the aux_stream in Llama4MinLatencyFusedMoE (#9035) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-11-13 09:09:52 -08:00
Ziyi Xiong
a7aaf50541
[TRTLLM-8084][feat] Enhance the overlap shceduler for two-model spec decoding (#8706) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-11-13 10:20:16 -05:00
William Zhang
121140cfec
[None][fixes] Add tool call parsing fixes and Qwen3 coder parser (#8817) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-11-13 04:34:38 -08:00
Kaiyu Xie
177ba7b0f1
[None] [fix] Disable UCC as WAR to MPI allgather issue before NGC PyTorch 25.12 upgrade (#9126) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-11-13 02:25:30 -08:00
Chang Liu
c37924f37b
[None][fix] Clear indexer k cache reference before release cuda memory (#9110) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-11-12 22:12:53 -08:00
Zhang Ge
49df731b96
[#6507][fix] Fix precision issue due to KV layout mismatch for split/concat kernels (#6917) 
Signed-off-by: ZhangGe6 <sjtu.zg123@gmail.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-11-13 12:14:58 +08:00
QI JUN
d1b003d31e
[TRTLLM-9212][chore] move MoeLoadBalancerConfig to llm_args.py (#9002) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-13 10:47:35 +08:00
Zhenhuan Chen
943b05e2d3
[TRTLLM-9179][feat] add pp_partition to customize each rank's layer number (#9003) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2025-11-13 10:34:17 +08:00
Chenghao Zhang
f1d637ec69
[None][fix] AutoDeploy: Use tmp folder for the load_moe_align (#9101) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-12 14:59:49 -08:00
dongxuy04
9241ccaf27
[None][feat] Enable EPLB for trtllm-gen and cutlass backend (#8886) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
 2025-11-12 12:30:27 -08:00
Patrice Castonguay
8a751a0e56
[None][chore] Remove is_disaggregated param in executor request queue (#9049) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-11-12 13:37:15 -05:00
Fanrong Li
780d4f9dc5
[None][feat] Add MTP>1 support for DS-v3.2 (#9045) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-12 09:56:12 -08:00
Neta Zmora
53491ffdb1
[#9023][feat] reduce AD graph optimization time for non-participating passes (#9024) 
Shorten AD graph optimization by 30% (measured on Nemotron-6):

A bug in the transformation interface marked all passes as not clean, regardless of what was reported by the transformation
Fix how the optimization passes report the results of their actions. Many passes report that the graph is not clean even when they didn't participate in the optimization. Each graph cleaning invocation can take several seconds.

Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
 2025-11-12 09:05:53 -08:00
Chang Liu
0b81173efa
[TRTLLM-9259][perf] Use torch.compile to fuse copy + layernorm within the LayerNorm module (#9052) 
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-11-11 18:11:00 -08:00
Lucas Liebenwein
aca56097cb
[None][fix] AutoDeploy: update nano3 accuracy test (#9061) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-11 12:26:31 -08:00
QI JUN
524754b6fd
[TRTLLM-8521][chore] remove circular dependency between model engine and cuda graph runner (#7572) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-11 10:13:45 -08:00
Chenghao Zhang
ec9cf715a2
[None][feat] AutoDeploy: Perf improvement for mamba layers (#8991) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-11 08:27:07 -08:00
Wanli Jiang
ebdd1cc8e0
[TRTLLM-8119][feat] Update doc/tests/chat_template for nano-v2-vlm (#8840) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-11-11 07:48:23 -08:00
mpikulski
20fd305bb6
[None][fix] type annotation (#9071) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-11 07:20:20 -08:00
mpikulski
b151de4a8f
[TRTLLM-8377][test] unit tests for TorchSampler batched sampling (#9012) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
Co-authored-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-11-11 07:16:42 -08:00
Guoming Zhang
b894dc2d70
[None][fix] Display the GPU memory information in GiB unit. (#9070) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-11-11 06:24:59 -08:00
mpikulski
979b3ae9ce
[TRTLLM-7723][feat] sampling using FlashInfer.sampling (#8581) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-11 03:21:19 -08:00
Yuxian Qiu
7aeac97e4e
[https://nvbugs/5622938][fix] Use async send_requests_to_next_pp. (#9041) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-11-11 14:19:44 +08:00
Lucas Liebenwein
6bf4e59267
[#8763][feature] AutoDeploy: configurable dtype for caching (#8812) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-10 22:17:14 -08:00
Chang Liu
7ceb5e5ab6
[TRTLLM-9198][perf] Add torch.compile + multi-stream support for k-cache scatter and weight scaling (#8988) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-11 12:33:30 +08:00
shuyixiong
1ccb799c9a
[None][chore] Relocate rlhf_utils.py (#8938) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-11-10 19:03:23 -08:00
Liao Lanyu
1fd11455d8
[https://nvbugs/5556998][fix] init_hf_modules in worker_main for models with trust_remote=true (#8931) 
Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
Co-authored-by: Lanyu Liao <lancelly@users.noreply.github.com>
 2025-11-11 10:30:37 +08:00
Frida Hou
f40e1f7496
[https://nvbugs/5625972][fix] Add context manager to fix FakeTensorProp (#9047) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-10 16:25:58 -08:00
mpikulski
edc91ba819
[None][fix] Improve type annotations on ResourceManager.get_resource_manager (#9013) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-10 15:06:16 +01:00
ChristinaZ
2e7769d1e8
[None][feat] Add customized topk and related unit tests for DSA (#8882) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-11-10 03:35:35 -08:00
bhsueh_NV
e8d4a56dd0
[None][fix] fix eagle3 accuracy issue on sm120 (#8944) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-11-10 14:02:03 +08:00
Fanrong Li
a7033a9193
[TRTLLM-9001][feat] add TP support for DeepSeek-V3.2 (#8943) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-11-10 12:16:01 +08:00
mpikulski
533add5056
[TRTLLM-8598][feat] enable n > 1 in OpenAI API with PyTorch backend (#8951) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-07 17:47:35 -08:00
hvagadia
6ff82ea24e
[None][feat] Allow env variable to specify spawn process IPC address (#8922) 
Signed-off-by: hvagadia <hvagadia@nvidia.com>
 2025-11-07 15:45:57 -08:00
Chang Liu
7081f254cf
[None][perf] Add custom indexer k cache scatter op (#8960) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-11-07 11:24:26 -08:00
Patrice Castonguay
d8ea0b967f
[None][fix] Moving transfer timeout test to test_llm_pytorch, fixing broken kv transfer timeout (#8892) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-11-07 07:33:51 -08:00
Yiqing Yan
c836ae5aaa
[None][chore] Bump version to 1.2.0rc3 (#9004) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-11-07 01:24:32 -08:00
mpikulski
5ef65872a3
[None][fix] type annotations in fuse_input_embeds (#8976) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-11-07 09:04:08 +01:00
Stefan Niebler
326a201473
[https://nvbugs/5508536][fix] Take Over (#8627): Reintroduce: Move stop_criteria to sample_async (#7041) (#8794) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-11-07 09:01:15 +01:00
QI JUN
1c6e490894
[TRTLLM-9065][chore] remove PyTorchConfig completely (#8856) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-06 22:37:03 -08:00
Eran Geva
990e674b71
[None][fix] Switch AD AllReduce strategy to NCCL (#8979) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-11-07 06:49:44 +02:00
xiweny
ee20e679a9
[https://nvbugs/5636986][fix] Fix DeepGemmMoe get_buffer calls (#8939) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: xiweny <13230610+VALLIS-NERIA@users.noreply.github.com>
 2025-11-06 19:57:19 -08:00
Cao Dong
b53961e972
[None][feat] Return logprobs incrementally in torch backend (#8785) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-11-07 10:23:39 +08:00
Chang Liu
1c19fd6868
[https://nvbugspro.nvidia.com/bug/5637012][fix] Bugfix when config is None for MLA (#8978) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-11-07 09:37:19 +08:00
jthomson04
fcae852cef
[None][fix] Fix KV cache clearing with KV Connector API (#8750) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2025-11-06 14:28:27 -08:00
Chenghao Zhang
1a78e7a3d6
[None][feat] AutoDeploy: Support Latent MOE for Nemotron (#8955) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-11-06 12:40:19 -08:00
dhansen-nvidia
ada93f1187
[https://nvbugs/5527655][feat] Add NUMA-aware CPU affinity autoconfig (#8805) 
Signed-off-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
Co-authored-by: Dan Hansen <1+dhansen-nvidia@users.noreply.github.com>
 2025-11-06 11:59:46 -08:00
Chenghao Zhang
ddf2d010e2
[TRTLLM-8814][feat] AutoDeploy: Use TRTLLM kernels for FP8 linear (#8820) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-11-06 11:00:10 -08:00
yunruis
51545560da
[TRTLLM-8803][feat] Add rope and uk-bgemm overlap for mla generation (#8495) 
Signed-off-by: yunruis <205571022+yunruis@users.noreply.github.com>
 2025-11-06 17:39:57 +08:00
Yilin Fan
b7798bfab8
[None][feat] Add trtllm_ prefix for exposed metrics (#8845) 
Signed-off-by: nv-yilinf <206948969+nv-yilinf@users.noreply.github.com>
 2025-11-06 15:27:18 +08:00
Yi Sun
cc12d33393
[None][feat] Deep Research Implemented with Scaffolding (#8452) 
Signed-off-by: Yi Sun <yisun0618@gmail.com>
 2025-11-06 10:33:28 +08:00
JadoTu
6bbb43f2b9
[None][feat] Add qwen3-next nvfp4 support (#8526) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-11-06 09:45:44 +08:00
Frida Hou
fb7f9831d3
[#8924][fix] Fix AutoDeploy pattern matcher for torch 2.9 (#8920) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-05 13:29:20 -08:00
Lucas Liebenwein
b181568d6f
[TRTLLM-8201][feat] Nemotron H MoE Sharding (#8744) 
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: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-11-05 12:35:29 -08:00
Chang Liu
e57d83c5dc
[TRTLLM-8768][chore] Fuse QK down_proj with indexer K + weight_proj for FP4 ckpt (#8771) 2025-11-05 07:57:09 -08:00
Yukun He
b9e5315dfb
[https://nvbugs/5623960][fix] Fix the logger once key issue and further compress log in AutoTuner. (#8873) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-11-05 15:25:43 +08:00
Shiyu Li
eeb56c2848
[None][feat] MNNVLAllreduce Kernel Refactor (#8018) 
Signed-off-by: Shiyu Li <timlee0212@outlook.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-11-05 08:49:47 +08:00
Frida Hou
11ded113cd
[#8389][fix] Update group attention matching to first map to custom torch attention (#8638) 
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-11-04 12:00:43 -08:00
shuyixiong
70e4d72ffa
[TRTLLM-8511][feat] Add update_weights and sleep_wakeup support for rl integration (#8302) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
Co-authored-by: Liwei Ma <liweim@nvidia.com>
Co-authored-by: Jonas Yang CN <joyang@nvidia.com>
 2025-11-04 10:19:24 -08:00
Bo Li
e4bf29bc66
[None][feat] Integrate MnnvlThroughput into TRTLLM MoE. (#8728) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-04 21:36:29 +08:00
Cao Dong
dddfcdd3bf
[None][fix] Fix bug of undefined py_topk_logprobs_vals (#8789) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-11-04 19:32:59 +08:00
Zhanrui Sun
4de31bece2
[TRTLLM-8994][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0 (#8838) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-11-04 18:59:34 +08:00
CarstyYou
4296c9553d
[TRTLLM-1234][feat] Add fp8 blockscaled Gemm for sm120 (#8844) 
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
 2025-11-04 18:10:36 +08:00
danielafrimi
2b58dba0f6 [https://nvbugs/5524714][fix] Fix TP sharding of fused-QKV weight scales in W4A16 AWQ (#8432) 
Signed-off-by: Daniel Afrimi <dafrimi@nvidia.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Patrice Castonguay
65c138108e [https://nvbugs/5552889][fix] fix: Prevent empty batch when using attention DP with disagg (#8372) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
xiweny
fcac2022e2 [https://nvbugs/5565565] [fix] fp8 wideep support sm103 (#8228) 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-11-04 16:42:31 +08:00
Yechan Kim
67208f1512
[None][fix] InputProcessor config naming convention fix (#8705) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-11-03 22:29:21 -08:00
HuiGao-NV
97674c3114
[TRTLLM-8690][feat] add more tensors to share buffers (#8691) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-11-03 21:08:01 -08:00
Yan Chunwei
ed297d7c2e
[None][chore] Optimize perf for the RPC executor and add some profile utilities to llm-api (#8415) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-11-03 17:59:49 -08:00
Matthias Jouanneaux
d0f107e4dd
[TRTLLM-5966][feat] Helix: add full MLA support for Helix (#8104) 
Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com>
 2025-11-04 09:06:58 +08:00
Li Min
89336fbf07
[None][fix] Fix cute dsl nvfp4 gemm autotune issue (#8761) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-11-03 22:55:45 +08:00
Yechan Kim
f48968b6cc
[TRTLLM-6928][fix] Refactor multimodal unittest (#8453) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-11-03 06:01:07 -08:00
Yechan Kim
00c0e6c440
[https://nvbugs/5523315][fix] Fix serve benchmark test (#8255) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-11-03 00:30:13 -08:00
Cao Dong
2ff772ef71
[None][feat] Add benchmark to DeepConf (#8776) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-11-03 16:05:50 +08:00
yufeiwu-nv
b4d17d1a4c
[TRTLLM-8991][test] Add Llama 3.3 70B model with different performance config (#8753) 
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
Co-authored-by: Larry Xu <197874197+LarryXFly@users.noreply.github.com>
 2025-11-03 13:34:06 +08:00
Chang Liu
f57dc01e6f
[https://nvbugs/5625380][chore] Remove multimodal related fields from decoder llm input (#8846) 2025-11-02 17:44:08 -08:00
Eran Geva
f8778230e3
[#8781][fix] Cache the AllReduce wrapper to avoid re-allocating workspace which caused a hang (#8803) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-11-02 15:30:39 +02:00
Yan Chunwei
1551ed8e5f
[https://nvbugs/5437384][test] CHERRY-PICK: fix trtllm-llmapi-launch multi tests (#8567) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-11-01 06:49:33 -07:00
Bo Li
4c5a8f4ec6
[None][fix] Rename: slot_count -> invalid_expert_id (#8783) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-11-01 21:36:59 +08:00
QI JUN
89e0117097
[TRTLLM-8836][chore] Create ModelEngine from LlmArgs (#8600) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-11-01 05:26:06 -07:00
Fanrong Li
f0dc746738
[TRTLLM-8541][feat] Add trtllm-gen sparse MLA kernels to support per-Tensor FP8 KV Cache (#8692) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Co-authored-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-10-31 14:38:31 -07:00
Suyog Gupta
3d0e38e074
[None][perf] AutoDeploy optimize _get_unique_value (#8822) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-10-31 04:57:10 -07:00
Anthony Chang
852e5060aa
[https://nvbugs/5558117][fix] Allow per-layer quant config from hf_quant_config.json (#8617) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-10-31 04:41:44 -07:00
Yukun He
1d4a186ace
[https://nvbugs/5623960][fix] Compress the warning log of AutoTuner when encountering tactic failures. (#8793) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-10-31 11:09:14 +08:00
Yuxian Qiu
025d2926df
[https://nvbugs/5599515][fix] Fix PP bubbles. (#8687) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-10-31 10:13:56 +08:00
Yilin Fan
f3224ccd32
[None][feat] Add disagg relay time to time breakdown tool (#8465) 
Signed-off-by: nv-yilinf <206948969+nv-yilinf@users.noreply.github.com>
 2025-10-30 18:21:45 -07:00
Chenghao Zhang
71c5576a44
[TRTLLM-8734][feat] AutoDeploy: Enable the nvfp4 for Nemotron MOE (#8737) 
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-10-30 12:33:08 -07:00
Tailing Yuan
ec31363a86
[None][fix] Layer wise benchmarks: use local models, lint (#8799) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-10-30 09:47:46 -07:00
Tailing Yuan
f9c7786dc8
[None][feat] Add layer wise benchmarks (#8777) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-10-30 20:29:34 +08:00
Anthony Chang
f666ad2f6b
[None][feat] Autotuner can iterate through all tactics for test purposes (#8663) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-10-30 13:11:25 +01:00
WeiHaocheng
cc286687c4
[None][feat] Refactor scaffolding streaming feature and fix openai wo… (#8622) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-10-30 16:02:40 +08:00
Void
6b755fd9f8
[None][fix] fix runtime error that bf16 input is not quantized to nvfp4 when use bf16 dispatch (#8507) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-10-30 15:06:54 +08:00
Yi Zhang
496b419791
[None][doc] Add doc for torch.compile & piecewise cuda graph (#8527) 
Signed-off-by: yizhang-nv <187001205+yizhang-nv@users.noreply.github.com>
 2025-10-29 21:15:46 -07:00
Simeng Liu
834a780655
[https://nvbugs/5599086][fix] Fix FP8 Linear module for spark (#8707) 
Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2025-10-29 13:58:19 -07:00
Iman Tabrizian
ae6875fe10
[TRTLLM-8976][feat] Move indexer-k-cache to KVCacheManager (#8699) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2025-10-29 08:04:26 -07:00
Leslie Fang
451959c60d
[TRTLLM-8763][chore] Deprecate pybind based GuidedDecodingConfig usage in torch backend (#8717) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-10-29 20:37:14 +08:00
Fanrong Li
a21697ead9
[None][fix] fix config loading for DeepSeek-V3.2 in trtllm-bench (#8729) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-10-29 05:17:16 -07:00
kris1025
e2c5a38879
[https://nvbugs/5534574][fix] disable spec decoding forever once the request spec decoding is disabled (#8446) 
Signed-off-by: linquanh <linquanh@nvidia.com>
 2025-10-29 19:28:43 +08:00
Yi Zhang
a69bd2a6fa
[https://nvbugs/5550409][fix] Disable torch compile in piecewise attention part to Avoid host overhead (#8708) 
Signed-off-by: yizhang-nv <187001205+yizhang-nv@users.noreply.github.com>
 2025-10-29 18:12:58 +08:00
Pengyun Lin
2aade46d18
[TRTLLM-8214][feat] Support Qwen3 tool parser (#8216) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-10-29 15:48:29 +08:00
Chang Liu
5f737b8dbe
[None][perf] Use fp8 quant kernel in DS3.2 indexer module (#8701) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-10-29 12:45:09 +08:00
Cheng Hang
15c293a90b
[None][feat] Enable nvfp4 cuda core for sm120 (#8620) 
Signed-off-by: Cheng Hang <chang@nvidia.com>
 2025-10-29 12:39:03 +08:00
Yechan Kim
bc26f4ce7c
[https://nvbugs/5549829][fix] Qwen2.5-VL TP > 1 + Quantized weight load fix (#8680) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-10-29 13:38:42 +09:00
Yechan Kim
cf8a1d2ef9
[https://nvbugs/5596377][fix] Fix mm dummy calculation (#8498) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-10-29 09:45:21 +09:00
Lizhi Zhou
24167d00eb
[TRTLLM-8431][doc] update public doc and example, add etcd auto-scaling tests (#8602) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-10-28 17:04:53 -07:00
Kaiyu Xie
227c288441
[TRTLLM-8827] [feat] Enable low precision alltoall for Cutlass and TRTLLMGen backends (#8675) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-10-29 07:56:48 +08:00
Mike Iovine
00161b315f
[https://nvbugs/5549111][fix] Fix 2-model overlap scheduler accuracy on very long prompts (#8076) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Michael Iovine <miovine@nvidia.com>
 2025-10-28 14:55:34 -07:00
Lucas Liebenwein
0ee71d95ec
[https://nvbugs/5606166][fix] AutoDeploy: use tuples for cudagraph shape lookup (#8658) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-28 10:52:43 -07:00
Anish Shanbhag
a09b38a862
[TRTLLM-8684][chore] Migrate BuildConfig to Pydantic, add a Python wrapper for KVCacheType enum (#8330) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-10-28 09:17:26 -07:00
William Zhang
cdc9e5e645
[None][fix] Properly raise error for nemotron H models (#8697) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-10-28 08:59:42 -07:00
Eran Geva
e051a05e6c
[#8694][fix] fix AutoDeploy cuda memory access failure in nvidia/NVIDIA-Nemotron-Nano-31B-A3-v3 (#8696) 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-10-28 13:21:43 +02:00
Erin
a966644a71
[None][fix] Change Ray submit() to use async RPC (#8636) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-10-28 00:56:13 -04:00
gramnarayan
88b0fbc8ff
[#8245][feat] Autodeploy: Guided Decoding Support (#8551) 
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-28 09:29:57 +08:00
Bo Li
9c4432f8a4
[TRTLLM-7318][feat] MnnvlThroughput AlltoAll implementation. (#7499) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-10-27 13:23:06 -04:00
nvxuanyuc
d1398c05e6
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127) 
Signed-off-by: Xuanyu Chen <xuanyuc@nvidia.com>
 2025-10-27 13:12:31 -04:00
Chenghao Zhang
b9b2802599
[None][feat] Autodeploy: Update the ssm to use slice (#8667) 
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
 2025-10-27 09:45:20 -07:00
mpikulski
7c8ba71b49
[TRTLLM-8832][feat] fully async _select_generated_logits with tests (#8628) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-27 16:15:32 +01:00
QI JUN
4fd58137a1
[TRTLLM-8933][chore] remove unused update_executor_config function (#8678) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-27 10:00:47 -04:00
Kaiyu Xie
c9b08790c2
[None] [test] Add MNNVL AlltoAll tests to pre-merge (#8601) 2025-10-27 21:39:44 +08:00
Chao Ni
0019d99e6d
[None][test] Add longbench v2 for long context evaluation (#8604) 
Signed-off-by: mni <125171826+baize97@users.noreply.github.com>
 2025-10-27 20:01:14 +08:00
zhanghaotong
1026069a2b
[None][feat] Add opentelemetry tracing (#5897) 
Signed-off-by: Zhang Haotong <zhanghaotong.zht@antgroup.com>
Signed-off-by: zhanghaotong <zhanghaotong.zht@antgroup.com>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Zhang Haotong <zhanghaotong.zht@alibaba-inc.com>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-10-27 18:51:07 +08:00
Tailing Yuan
858d6437c1
[None][fix] Fix ModelConfig.from_pretrained get quant config file (#8647) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-10-27 11:02:24 +08:00
Jinyang Yuan
0a0f93d4a8
[None][fix] Fix the performance issue of FP8 blockwise grouped GEMM when using attention DP (#8501) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-10-27 10:18:19 +08:00
Chenghao Zhang
a6d20f6f9b
[None][feat] AutoDeploy: Add FP8 MOE for Nemotron (#8599) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-10-25 15:26:45 -04:00
Wanli Jiang
95be56e56b
[TRTLLM-8238][feat] Add EVS support for nano-v2-vlm (#8024) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Co-authored-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-10-25 05:43:27 -04:00
Simeng Liu
2b27810198
[https://nvbugs/5494718][fix] Fix Single GPU Multi-node issue and OOM on DGX Spark (#8514) 
Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2025-10-24 19:09:07 -07:00
Erin
812bc8c954
[TRTLLM-8513][feat] Add back worker extension (#8482) 
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-10-24 20:30:28 -04:00
jthomson04
02081e2390
[None][feat] Support KV Connector with Disagg Prefill Worker (#8246) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2025-10-24 11:09:06 -07:00
Chang Liu
e47c787dd7
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-10-24 13:40:41 -04:00
Yechan Kim
2d86d6be40
[TRTLLM-8737][feat] Support media_io_kwargs on trtllm-serve (#8528) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-10-24 12:53:40 -04:00
Aurelien Chartier
cdf0403c64
[None][feat] Pass KvCacheRetentionConfig to torch LlmRequest (#8634) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-10-24 06:44:34 -07:00
Chuang Zhu
2420918e5b
[TRTLLM-7078][chore] optimal kvcache transfer for VWSA (#7952) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-10-24 08:58:16 -04:00
Suyog Gupta
f512ddaeef
[None][feat] add skip condition in AutoDeploy's triton fused moe kernel (#8632) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-10-24 08:46:17 -04:00
Wanli Jiang
f448043d88
[None][feat] Support base64 video input (#8458) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-10-24 10:23:13 +08:00
Zheng Duan
e666a704f5
[None][doc] add visualization of perf metrics in time breakdown tool doc (#8530) 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
 2025-10-23 22:09:21 -04:00
QI JUN
6ee1c87595
[TRTLLM-8817][chore] Set default value of KvCacheConfig.free_gpu_memory_fraction explicitly (#8561) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-24 08:55:49 +08:00
h-guo18
23920223ab
[#4585][feat] Replace unified attention before export (#8303) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
 2025-10-23 18:02:04 -04:00
QI JUN
cc81028547
[TRTLLM-8812][chore] Limit the scope of pybind based CacheTransceiverConfig (#8558) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-23 10:32:09 -04:00
Robin Kobus
3a5845e293
[TRTLLM-8714][fix] update create_input_processor to handle custom checkpoint format (#7811) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-10-23 10:27:56 +02:00
Shijie
928247a3f9
[https://nvbugs/5451205][feat] Add cuBLASLt NVFP4 GEMM backend support (#7943) 
Signed-off-by: Shijie Wang <jaywan@nvidia.com>
 2025-10-23 15:55:10 +08:00
Suyog Gupta
2956978da3
[None][feat] Enable rms norm fusion for Nemotron MOE (#8563) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-23 00:09:42 -04:00
sunnyqgg
ea3e0eea51
[TRTLLM-7954][feat] Target model KV cache rellocation (#8421) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-10-23 09:36:50 +08:00
Anthony Chang
8a3b870e09
[None][feat] Update TRTLLM MoE MxFP4 cubins; autotune tileN (#8156) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2025-10-23 09:14:18 +08:00
Anish Shanbhag
15de45d782
[TRTLLM-8682][chore] Remove auto_parallel module (#8329) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-10-22 20:53:08 -04:00
Leslie Fang
e5865de518
[TRTLLM-8754][chore] Refine PyTorchModelEngine with llm args (#8493) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-10-22 20:03:18 -04:00
Patrice Castonguay
879039f6d5
[https://nvbugs/5429636][feat] Kv transfer timeout (#8459) 
Signed-off-by: raayandhar <raayan.dhar@gmail.com>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: raayandhar <raayan.dhar@gmail.com>
 2025-10-22 09:29:02 -04:00
Yan Chunwei
f81caf5491
[None][chore] replace print_colored_debug with logger_debug (#8417) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-10-22 17:54:38 +08:00
Yan Chunwei
3f9dbc76c0
[None][fix] fix rpc unique addr related issue (#8419) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-10-22 04:47:18 -04:00
Yiqing Yan
b04e51291a
[None][chore] Bump version to 1.2.0rc2 (#8562) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-10-22 14:35:05 +08:00
sunnyqgg
90080e0e09
[https://nvbugs/5556020][fix] test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3 dimension mismatch (#8517) 
Signed-off-by: qgai <qgai@nvidia.com>
 2025-10-22 09:58:22 +08:00
Leslie Fang
50d4e5bc06
[TRTLLM-8483][chore] Refine scheduler_config and peft_cache_config in create_py_executor (#8451) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-10-22 08:33:48 +08:00
Chenghao Zhang
bac9e8c2ad
[None][feat] AutoDeploy: Add Nemotron MOE support for AutoDeploy (#8469) 2025-10-21 15:32:01 -07:00
Lizhi Zhou
23d5280a90
[TRTLLM-7843][feat] implement disagg cluster auto-scaling (#8215) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-10-21 17:25:07 -04:00
Lucas Liebenwein
9b54b3bfaf
[None][chore] AutoDeploy: replace HF's deprecated keyword torch_dtype --> dtype (#8510) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-21 17:07:06 -04:00
YueWeng
8dc4aac5b6
[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-10-21 11:11:04 -04:00
Pengyun Lin
a4227cf1b0
[None][feat] Support Qwen3 reasoning parser (#8000) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-10-21 14:08:39 +08:00
Bo Li
ebb62e17d8
[None][feat] Add alltoall to trtllm-gen MoE backend. (#8481) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-10-21 12:42:54 +08:00
mpikulski
87eb5086fb
[None][fix] restore list[list[list[int]]] in add_token (#8502) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-20 22:34:57 -04:00
Yechan Kim
85d5aa7763
[None][feat] Support kv_cahce_reuse for HyperCLOVAX-Vision model (#7789) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-10-21 11:11:24 +09:00
Suyog Gupta
7050b1ea49
[#8272][feat] Enable chunked prefill for SSMs in AutoDeploy (#8477) 
Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-10-20 15:31:52 -07:00
Lucas Liebenwein
55c468b218
[#8461][feat] AutoDeploy: trtllm-serve bug fix + unit test (#8462) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-20 16:06:39 -04:00
Pamela Peng
b818a912d7
[https://nvbugs/5540752][fix] Support quantized Phi4 MM models (#8190) 
Signed-off-by: Pamela <179191831+pamelap-nvidia@users.noreply.github.com>
 2025-10-20 06:36:09 -04:00
mpikulski
97ce0ecefe
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements (#8398) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-20 11:15:41 +02:00
ChristinaZ
c8b9998acb
[TRTLLM-8637][feat] Optimize the routing kernel for DeepseekV3 (MoE CUTLASS backend); Add support for KimiK2 and Qwen-next (MoE TRTLLM backend) (#7761) 
Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
 2025-10-20 10:08:31 +08:00
Bo Deng
dd25595ae8
[TRTLLM-7964][infra] Set nixl to default cache transceiver backend (#7926) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
 2025-10-19 19:24:43 +08:00
jthomson04
852316886e
[None][fix] Fix KV event consumption (#6346) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2025-10-18 15:41:26 -07:00
Lucas Liebenwein
41169fb20c
[None][feat] AutoDeploy: chunked prefill support (#8158) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-18 00:47:35 -07:00
QI JUN
4a8ac8dd62
[TRTLLM-8480][chore] clean create_py_executor API (#8412) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-17 23:52:02 -04:00
Wanli Jiang
58b43a6dab
[None][fix] Fix get_num_tokens_per_image for nano-v2-vlm (#8425) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-10-18 08:51:35 +08:00
Kyle McGill
136e0e6882
[None][feat] Enable CUDA graph support for KvConnectorWorker API (#8275) 
Signed-off-by: Kyle McGill <kmcgill@nvidia.com>
Signed-off-by: Kyle McGill <101670481+nv-kmcgill53@users.noreply.github.com>
 2025-10-17 18:09:03 -04:00
Anish Shanbhag
5ff4f88be6
[TRTLLM-8683][chore] Migrate PluginConfig to Pydantic (#8277) 
Signed-off-by: Anish Shanbhag <ashanbhag@nvidia.com>
 2025-10-17 16:13:22 -04:00
h-guo18
55fed1873c
[None][chore] AutoDeploy: cleanup old inference optimizer configs (#8039) 
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-17 15:55:57 -04:00
Grzegorz Kwasniewski
bb7fdcebf4
[TRTLLM-8201][feat] Topological graph helpers (#8457) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-10-17 12:34:19 -04:00
zhhuang-nv
7a2bab93f0
[None][test] Add post merge test for Seed-OSS-36B-Instruct (#8321) 
Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
 2025-10-17 02:30:33 -07:00
Tracin
dd06612d0e
[https://nvbugs/5540138][fix] Fix shape error when duplicating kv. (#8390) 
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
 2025-10-17 10:07:29 +08:00
John Calderon
46ee7acb33
[TRTLLM-6780][fix] Add multimodal data to dummy requests during memory profiling (#7539) 
Signed-off-by: John Calderon <johncalesp@gmail.com>
Signed-off-by: John Calderon <jcalderon@nvidia.com>
Signed-off-by: john calderon <jcalderon@nvidia.com>
Signed-off-by: John Calderon <jcalderon@nvidia>
 2025-10-16 17:49:22 +02:00
Jin Li
d594c2d0ff [https://nvbugs/5537348][fix] Use device tensor index for MTP (#8062) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-10-16 22:46:19 +08:00
Yechan Kim
9587f099ac [https://nvbugs/5547434][fix] Fix Qwen2.5-VL device_path error (#8057) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-10-16 22:46:19 +08:00
Yukun He
179c7dc501 [https://nvbugs/5536131][fix] Fix illegal access issue when scale is not provided in Llama3/4. (#7960) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-10-16 22:46:19 +08:00
Enwei Zhu
57a4ef870a [None][fix] Fix chunked prefill state of draft request (#8067) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-10-16 22:46:19 +08:00
Wangjue Yao
9865d3d770
[None][feat] Support cached tokens for Openai server (#7637) 
Signed-off-by: wjueyao <wyao123@terpmail.umd.edu>
Co-authored-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-10-16 20:51:37 +08:00
chinamaoge
ee588a73ac
[None][fix] Fix the error where checkpoint_dir is assigned as NONE wh… (#8401) 
Signed-off-by: maoge <maoge23@qq.com>
Co-authored-by: maoge <maoge23@qq.com>
 2025-10-16 13:37:43 +08:00
Min Yu
0a0159fdd8
[https://nvbugs/5378031] [feat] W4A8 AWQ MoE supports Per Expert Pre-quant Scale Factor for PyT backend (#7286) 
Signed-off-by: Min Yu <171526537+yumin066@users.noreply.github.com>
 2025-10-16 11:07:48 +08:00
Cao Dong
e75b4f9f65
[None][feat] Dev DeepConf (#8362) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-10-16 11:01:31 +08:00
Wanli Jiang
ebf0e51206
[TRTLLM-8579][feat] Support quantized model for nano-v2-vlm (#8304) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-10-16 09:44:11 +08:00
Yan Chunwei
206cf31705
[https://nvbugs/5560921][fix] GenerationExecutor RPC (#8209) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-10-16 09:05:22 +08:00
Chuang Zhu
40d129a415
[None][fix] Fix cache buffer size for window (#8320) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-10-16 09:01:11 +08:00
HuiGao-NV
e265eb5fe9
[None][feat] reuse cudagraph memory pool in normal forward flow (#8095) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-10-16 07:08:44 +08:00
dongfengy
7a0aa64973
[None][fix] Refactor triton paddings (#6980) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
Signed-off-by: dongfengy <99041270+dongfengy@users.noreply.github.com>
Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>
 2025-10-15 12:59:01 -07:00
QI JUN
65ec01b257
[TRTLLM-8532][chore] clean warmup method of ModelEngine (#8264) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-15 08:40:58 -07:00
Yukun He
56c20665a9
[TRTLLM-4501][feat] Add input tensor pre-hook function API for the tuning process. (#6924) 
Some tunable ops require a more realistic data distribution, for instance, a shape-associated tensor. Thus, a customizable pre-hook function can be declared in the tuning config to modify the input tensor before the tuning process.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-10-15 21:18:11 +08:00
mpikulski
0510b34588
[TRTLLM-8551][feat] add cache_salt in LLM.generate and refactor test_return_logits.py (#8317) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-15 02:53:57 -07:00
mpikulski
93a4b7f1b6
[None][chore] update torch_dtype -> dtype in 'transformers' (#8263) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-15 17:09:30 +09:00
QI JUN
616d1df7a0
[None][chore] set the default value of max_num_tokens explicitly (#8208) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-14 23:03:02 -07:00
sychen52
6a6124dcb5
[OMNIML-2336][feat] w4a8 nvfp4 fp8 exports scale factor properly (#8180) 
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
Co-authored-by: Shiyang Chen <shiychen@omniml-a6.nvidia.com>
 2025-10-15 13:41:27 +08:00
Lizhi Zhou
22471ecc67
[TRTLLM-7846][feat] implement etcd storage for disagg cluster (#8210) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-10-14 16:48:41 -04:00
Tailing Yuan
8444a50d3a
[None][fix] Fix is_post_quant_all2all_supported for MNNVL (#8355) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-10-14 11:49:21 -07:00
shuyixiong
6776caaad1
[TRTLLM-8507][fix] Fix ray resource cleanup and error handling in LoRA test (#8175) 
Signed-off-by: shuyix <219646547+shuyixiong@users.noreply.github.com>
 2025-10-14 23:46:30 +08:00
Fanrong Li
0d20a8fd61
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
Co-authored-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
 2025-10-14 08:23:16 -07:00
Cao Dong
62cea877b1
[None][feat] Move StreamGeneration to scaffolding main directory (#8347) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-10-14 17:16:04 +08:00
Yuxian Qiu
3450fe9944
[None][fix] Fix dummy load format for key models. (#7993) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-10-14 11:18:39 +08:00
Aurelien Chartier
9bc055faf1
[None][fix] Disable DeepGEMM for Qwen3 MoE Attention layers (#8087) 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
 2025-10-13 18:38:47 -07:00
Lucas Liebenwein
22aa4ac08c
[None][feat] AutoDeploy: VLMs with subgraphs + cudagraph/compile (#8203) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-10-13 17:34:09 -07:00
Zheyu Fu
bac665e650
[TRTLLM-7412][feat] Turn off spec decode when the rolling average acceptance length drops below threshold. (#7283) 
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
 2025-10-13 15:51:14 -07:00
Grzegorz Kwasniewski
ea4658197f
[TRTLLM-6342][feat] Factory TP sharding of quantized models (#8123) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
Co-authored-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>
 2025-10-13 14:04:46 -07:00
Yuxian Qiu
bd740c9ba6
[None][fix] Avoid unnecessary concat in attn_output_gate case. (#8094) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-10-13 12:59:40 -07:00
Robin Kobus
db8c63b9b1
[TRTLLM-4517] [feat] Additional model outputs (#7206) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-10-13 15:33:18 +02:00
Cao Dong
d882c92a84
[None][fix] Fix EventLoopShutdownError (#8260) 
Signed-off-by: Dong Cao <docao@nvidia.com>
 2025-10-13 17:31:33 +08:00
Po-Han Huang (NVIDIA)
6fc6f70a68
[https://nvbugs/5441729][test] Fix test_modeling_llama_min_latency.py failures (#7478) 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
 2025-10-13 15:35:02 +08:00
Leslie Fang
8d1b068b1a
[TRTLLM-8477][chore] Replace KvCacheConfigCpp with KvCacheConfig inside PyExecutor (#8259) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2025-10-13 14:55:36 +08:00
DylanChen-NV
d6e315e9ff
[None][feat] Add torch compile support for cuda core GEMM OP (#8261) 
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
 2025-10-12 20:57:17 -07:00
amitz-nv
fac47e2826
[https://nvbugs/5510879][fix] Fix pytorch & TRT-python flows fused LoRA adapter modules weight split with TP>1 (#8063) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-10-12 12:29:52 -07:00
kris1025
a7ea544dbe
[TRTLLM-7384][feat] enable rejection sampling for CDL (#7731) 
Signed-off-by: linquanh <linquanh@nvidia.com>
 2025-10-12 20:38:48 +08:00
Ziyi Xiong
efd4ffa03b
[https://nvbugs/5534705][fix] Skip unnecessary CUDA graph capture (#8050) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-10-11 13:26:55 +08:00
Yilin Fan
2695d70d42
[None][feat] Add request timing breakdown option in benchmark_serving (#8128) 
Signed-off-by: nv-yilinf <206948969+nv-yilinf@users.noreply.github.com>
 2025-10-10 09:24:54 -07:00
QI JUN
48c15d805c
[https://nvbugs/5558167][fix] update canceled_req_ids correctly for canceled requests (#8207) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-10-10 18:58:26 +08:00
HuiGao-NV
795a051765
[None][chore] Print log with time for starting to load safetensor weights (#8218) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2025-10-10 13:54:54 +08:00
mpikulski
7b6803b6e9
[TRTLLM-7769][chore] document the role of 'd2t' (#8174) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-09 13:13:50 -04:00
Lizhi Zhou
fdf29ab8fa
[TRTLLM-7846][feat] Http disagg-cluster management implemention (#7869) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-10-09 09:44:01 +08:00
dongfengy
9f2a3ae88c
[None][fix] Restrict tinygemm use to certain SMs (#8182) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
Signed-off-by: dongfengy <99041270+dongfengy@users.noreply.github.com>
 2025-10-08 17:55:57 -07:00
mpikulski
8298e93bd8
[TRTLLM-8414][chore] BREAKING CHANGE: refine sampling strategy selection (#8132) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-08 15:46:50 +02:00
Sergey Klevtsov
017583a949
[https://nvbugs/5488576][fix] Propagate disable_finalize_fusion config flag in WIDEEP MoE backend (#8141) 
Signed-off-by: Sergey Klevtsov <sklevtsov@nvidia.com>
 2025-10-07 14:44:54 -07:00
Mike Iovine
7facac077b
[None][fix] Fix MTP illegal memory access (#8161) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-10-07 14:02:55 -04:00
Faraz
27a5091fcb
[None][feat] GPT-OSS Sm120/Sm121 Support (#7937) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Signed-off-by: list <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: Vincent Huang <vincenth@nvidia.com>
Co-authored-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Co-authored-by: Vincent Huang <vincenth@nvidia.com>
 2025-10-06 16:59:06 -04:00
Izzy Putterman
f2657c1ae9
[None][fix] Eagle: Attention DP (#7939) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2025-10-06 16:52:35 -04:00
mpikulski
98b3af4d4e
[TRTLLM-8413][chore] resolve sampling defaults in OpenAI API backend (#8121) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2025-10-06 06:09:43 -07:00
Yan Chunwei
54ab9767b5
[None][chore] fix llmargs conflict (#8152) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
 2025-10-06 02:34:27 -07:00