kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 15:55:08 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
5,010 Commits 29 Branches 68 Tags 2 GiB
ffc0f54959
Commit Graph

1566 Commits

Author SHA1 Message Date
William Zhang
ffc0f54959
[https://nvbugs/5848756][fix] Re-take ownership of mrope tensors in prefill worker (#11217) 
* Why?

Previously, the mrope tensors' IPC handles would just be forwarded from
encode -> prefill -> decode workers. While this is fine for the
prefill worker, it is not for the decode worker, since by the time it
tries to rebuild those tensors, they could have been garbage collected
due to their refcounts reaching zero in the producer (encode) worker.

This could lead to nasty runtime errors when running E/P/D
disaggregated serving.

* What?

This commit fixes this by having the prefill worker take ownership of
those reconstructed tensors, and stand up new copies for the decode
worker.

Closes: NvBug 5848756

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2026-02-06 22:37:42 -05:00
Iman Tabrizian
18e611da77
[https://nvbugs/5863392][fix] fix partial reuse disabled for disagg (#11247) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2026-02-06 14:23:51 -05:00
Shi Xiaowei
b1268e1b37
[TRTLLM-9527][feat] Modularization of the transceiver for KV manager v2 (step 4) (#11225) 
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
 2026-02-06 07:15:18 -05:00
Yueh-Ting (eop) Chen
383c5921c2
[https://nvbugs/5756028][fix] Fix VSWA initialization with spec-dec and boundary condition in context input preparation (#10798) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2026-02-06 14:28:47 +08:00
Chenghao Zhang
9644f024bd
[None][feat] AutoDeploy: add triton backend for causal conv (#11124) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2026-02-05 21:33:00 -08:00
Chenghao Zhang
d160439ef9
[#11148][feat] AutoDeploy: Better structure the custom op (#11152) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2026-02-05 21:32:22 -08:00
yifeizhang-c
5521c7b7e7
[TRTLLM-9457][feat] Add cute dsl fp8 gemm for Blackwell (#10130) 
Added FP8 cute dsl gemm and batch gemm.

Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
 2026-02-06 09:49:30 +08:00
Chuang Zhu
a9d4927235
[TRTLLM-10752][chore] set default val of max_num_tokens_in_buffer as max_seq_len or max_input_len (#11082) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2026-02-05 14:54:00 -05:00
Harris Nover
a7494a5ff4
[None][chore] Remove outdated comment in model_engine.py (#11240) 
Signed-off-by: Harris Nover <249353502+hnover-nv@users.noreply.github.com>
 2026-02-05 13:54:46 -05:00
jthomson04
d778b26062
[None][fix] Reduce host memory usage during model loading (#11119) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2026-02-05 08:57:40 -08:00
mpikulski
7d235cfb23
[TRTLLM-10030][chore] promote SampleState to TypeVar + typing fixes (#11281) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2026-02-05 16:33:22 +01:00
chenfeiz0326
eae480b713
[https://nvbugs/5820874][fix] Adjust deepgemm tuning buckets to cover larger num_tokens's scope (#11259) 
Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>
 2026-02-05 23:12:38 +08:00
mpikulski
719e82c429
[TRTLLM-10030][perf] beam search (remove GPU sync + fix batching + refactor) (#11276) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2026-02-05 15:33:51 +01:00
Yuewei Na
0d18b2d7a4
[None][feat] Add priority-based KV cache offload filtering support (#10751) 
Signed-off-by: Yuewei Na <yna@nvidia.com>
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
 2026-02-05 05:22:56 -05:00
xxi
4c1d9d0c10
[None][chore] Pass without_comm to cutlass and deepgemm (#11229) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-02-05 02:07:59 -05:00
Yi Zhang
ada463d15d
[None][fix] Fix comments for kv cache manager v2 (#11207) 
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2026-02-04 23:31:29 -05:00
dongfengy
0bd4630cd1
[https://nvbugs/5854860][fix] Fix cutedsl argmax on sm120 (#11181) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2026-02-04 17:15:31 -05:00
Grzegorz Kwasniewski
d90a8e5700
[TRTLLM-10673][feat] Improved layer classification for sharding (#10718) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2026-02-04 18:06:10 +01:00
Lucas Liebenwein
925d911fc0
[#10966][feat] AutoDeploy: kv cache manager integration [2/2] (#11149) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2026-02-04 09:44:27 -05:00
Yueh-Ting (eop) Chen
f6fff18142
[https://nvbugs/5624818][fix] Work around accuracy issue by enforcing paged_context_fmha on Hopper for fmha_v2 (#11192) 
Signed-off-by: eopXD <yuehtingc@nvidia.com>
 2026-02-04 19:21:50 +08:00
xxi
02b80bfd58
[TRTLLM-9111][feat] provide the uniform test framework to test all MoE backends (#11128) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-02-04 15:57:56 +08:00
Gal Hubara-Agam
de6931bbfd
[None][fix] Fix selective_state_update perf regression for T=1 decode path (#11194) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-02-04 09:01:34 +02:00
Taylor Yeonbok Lee
f9e6045f39
[#11086][feat] Optimize Auto Deploy weight loading by preloading weights to CPU (#11059) 
Signed-off-by: Taylor Yeonbok Lee <249374542+taylor-yb-lee@users.noreply.github.com>
 2026-02-03 13:23:10 -08:00
Lizhi Zhou
f9c4bdf6cf
[TRTLLM-8921][feat] implement gen-first disagg_service (#11020) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-02-03 15:46:11 -05:00
Chenjie Luo
2532eb5adc
[None][fix] Align kv_scales with modelopt HF checkpoint (#10745) 
Signed-off-by: Chenjie Luo <108829653+cjluo-nv@users.noreply.github.com>
 2026-02-03 08:03:42 -05:00
gramnarayan
585fbb2734
[#10826][feat] AutoDeploy: Eagle One-Model [2/n]: Prefill-Only Implementation (#11073) 
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
 2026-02-02 09:51:10 -08:00
Izzy Putterman
3ef8a4639b
[None][feat] Nemotron H: Eagle3 support (#11131) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2026-02-02 10:26:25 -05:00
Rundong Li
f1b85fea4c
[None][feat] Integrate cuda.tile RMS norm kernels (#9725) 
Signed-off-by: Rundong (David) Li <davidli@nvidia.com>
Co-authored-by: Jinman Xie <jinmanx@nvidia.com>
Co-authored-by: Alexey Bylinkin <abylinkin@nvidia.com>
Co-authored-by: Qiqi Xiao <qiqix@nvidia.com>
Co-authored-by: Biao Wang <biaow@nvidia.com>
Co-authored-by: Thomas Schmid <thschmid@nvidia.com>
 2026-02-02 19:44:27 +08:00
Mike Iovine
13b0ab9c0e [None][fix] Fix MTP 1-model sampler (#10369) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-02-02 16:26:46 +08:00
Mike Iovine
d9aef94431 [https://nvbugs/5814914][fix] Fix llama sm120 spec dec (#10765) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-02-02 16:26:46 +08:00
Enwei Zhu
ccdd8461ac [None][fix] Always reset drafting states for GuidedDecoder (#10899) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-02-02 16:26:46 +08:00
Michal Guzek
fafc22e3d4 [https://nvbugs/5691730][fix] Have LoRa bf16 ckpts work with Llama 3.3-70B-fp8 (#9808) 
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
Signed-off-by: Michal Guzek <moraxu@users.noreply.github.com>
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Co-authored-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2026-02-02 16:26:46 +08:00
Yi Zhang
0306c0f12c
[TRTLLM-9766][feat] Integration of the KVCacheManager V2 to TRTLLM Runtime (#10659) 
Signed-off-by: yizhang-nv <187001205+yizhang-nv@users.noreply.github.com>
 2026-02-02 14:29:02 +08:00
Liao Lanyu
fef0e4b17d
[TRTLLM-10666][chore] Refactor request fetching logic for better separation of concerns (#10988) 
Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
Signed-off-by: Lance Liao <108499334+lancelly@users.noreply.github.com>
Signed-off-by: Liao Lanyu <108499334+lancelly@users.noreply.github.com>
Co-authored-by: Lanyu Liao <lancelly@users.noreply.github.com>
 2026-02-02 10:36:08 +08:00
shuyixiong
278ced972b
[TRTLLM-9771][feat] Allow overriding quantization configs (#11062) 
Signed-off-by: shuyixiong <219646547+shuyixiong@users.noreply.github.com>
 2026-01-31 10:48:51 -05:00
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
Guoming Zhang
6bace84167
[TRTLLM-10398][feat] Enable TRTLLM moe backend for Nemotron Super (#10791) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2026-01-31 13:48:25 +08:00
Balaram Buddharaju
531f85dc9b
[None][feat] Perfect routing for Deepseek models (#11127) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-30 23:46:35 -05:00
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
Liao Lanyu
f2dd0ee128
[None][chore] Correct sorting order for attention DP scheduling to prioritize non-relaxed requests (#11106) 
Signed-off-by: Lance Liao <108499334+lancelly@users.noreply.github.com>
 2026-01-30 16:06:48 +08:00
dongfengy
4f0c1b2489
[TRTLLM-10733][feat] Make TRTLLM MOE the default one for GPTOSS on Blackwell (#11074) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2026-01-29 23:59:19 -08:00
Jin Li
ef268e2062
[TRTLLM-9904][feat] Changes for future KVCacheV2 MTP support (#11029) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2026-01-30 01:49:17 -05:00
Necofish
144b61715f
[None][fix] Add missing absolute pe in Qwen3-VL Vision Encoder (#11065) 
Signed-off-by: Necofish <liuxiangyang@mail.ustc.edu.cn>
 2026-01-30 09:59:36 +09:00
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
Harris Nover
ab7dd34bbe
[None][chore] Consolidate duplicate kv cache reuse variables. (#10935) 
Signed-off-by: Harris Nover <249353502+hnover-nv@users.noreply.github.com>
 2026-01-29 11:03:27 -08:00
Stefan Niebler
7d31532850
[TRTLLM-10312][perf] Improve performance of _write_finish_reasons in TorchSampler (#10459) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2026-01-29 11:06:09 -05:00
Balaram Buddharaju
c7a86f89de
[TRTLLM-10264][feat] Support attention DP + Helix CP (#10477) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-29 02:57:13 -05:00
Tailing Yuan
91528365a9
[None][feat] Add performance alignment to layer-wise benchmarks (#11018) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2026-01-29 14:01:51 +08:00
Enwei Zhu
34a730aaf7
[None][fix] Fix enable_alltoall passed to CutlassFusedMoE (#11016) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2026-01-29 12:11:07 +08:00