kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-22 19:52:38 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
2,130 Commits 28 Branches 61 Tags 2.2 GiB
5eefdf2c75
Commit Graph

606 Commits

Author SHA1 Message Date
Yechan Kim
ee6ab5be96
chore: add EXAONE4 accuracy test (#6397) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-08-04 10:14:16 +08:00
Jinyang Yuan
df90202b51
[fix] Fix DeepSeek w4a8 weight loading (#6498) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-08-04 10:12:06 +08:00
Chuang Zhu
542f552d0b
use cudaSetDevice to create context ,fix nvbug 5394497 (#6403) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-08-03 13:32:55 -04:00
Shunkangz
67a3fd858b
[None][feat] Add support of scheduling attention dp request (#6246) 
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
 2025-08-01 20:38:01 -04:00
Lucas Liebenwein
5247df6ae2
[AutoDeploy] merge feat/ad-2025-07-22 (#6520) 
Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Signed-off-by: Gal Agam <ghubaraagam@cw-dfw-cs-001-login-01.cm.cluster>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: haoguo <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Co-authored-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com>
Co-authored-by: Gal Agam <ghubaraagam@cw-dfw-h100-004-328-012.cm.cluster>
Co-authored-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Co-authored-by: nvchenghaoz <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Co-authored-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
 2025-08-01 08:51:08 -07:00
brb-nv
7447d6ed85
[TRTLLM-6657][feat] Add LoRA support for Gemma3 (#6371) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-08-01 09:19:54 -04:00
liji-nv
1daa8c3232
[https://nvbugs/5340941][https://nvbugs/5375785] - fix: Wrap attentio… (#6355) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-08-01 07:38:06 -04:00
Robin Kobus
d3c14682f0
refactor: Remove unused buffers and bindings from sampler (#6484) 
Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-08-01 00:43:03 -04:00
Jaedeok Kim
fbee279909
fix: remove duplicate layer multiplication in KV cache size calculation (#6481) 
Signed-off-by: Jaedeok Kim <jaedeokk@nvidia.com>
 2025-07-31 22:34:34 -04:00
Zongfei Jing
7bb0a78631
Deepseek R1 FP8 Support on Blackwell (#6486) 
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-08-01 10:26:28 +08:00
Yukun He
00059de380
chore: Improve the AutoTuner log information. (#6368) 
* Change the fallback alert from DEBUG to WARNING level and only do it once.
* Add debug information for profiling cache right after the warmup phase.
* Change the level of exception message during tactic profiling from ERROR to WARNING level. All exception details are pushed to the DEBUG level.
* Other trivial refinements and cleanups.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-08-01 09:19:52 +08:00
brb-nv
2eca0d5925
fix: Fix poor generation with FP8 Gemma3 1B checkpoint (#6499) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-07-31 17:18:23 -07:00
Simeng Liu
8cf3faa26a
[feat] Auto-enable ngram with concurrency <= 32. (#6232) 
Signed-off-by: Simeng Liu <simengl@nvidia.com>
Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: Mike Iovine <mike.iovine7@gmail.com>
Co-authored-by: Mike Iovine <miovine@nvidia.com>
Co-authored-by: Mike Iovine <mike.iovine7@gmail.com>
 2025-07-31 18:45:51 -04:00
Ziyi Xiong
8062e0fe7c
[TRTLLM-6392][feat] Support turning on/off spec decoding dynamically (#6363) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-07-31 15:31:39 -04:00
shaharmor98
0c42f54a39
Bugfix/fix nemotron nas lora support (#6380) 
Signed-off-by: Shahar Mor <17088876+shaharmor98@users.noreply.github.com>
 2025-07-31 13:39:35 -04:00
amitz-nv
1ee7a08d2b
[5830][feat] Improve LoRA cache memory control (#6220) 
Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-07-31 09:26:38 +03:00
dongjiyingdjy
17e0d0fb1a
fix: fix illeagel memory access (#6437) 
Signed-off-by: Jiying Dong <87510204+dongjiyingdjy@users.noreply.github.com>
 2025-07-31 10:01:34 +08:00
Enwei Zhu
4b299cb77e
feat: Support structural tag in C++ runtime and upgrade xgrammar to 0.1.21 (#6408) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-07-31 09:53:52 +08:00
Vadim Gimpelson
25cd4f215e
[PERF] Move calculation Qwen2-VL's rotary_cos_sin to LLM worker process (#6004) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
 2025-07-31 09:35:24 +09:00
Wanli Jiang
9632dba02e
feat: TRTLLM-6450 update long rope for phi3.5/phi4-mini/phi4-mm (#6353) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-07-30 09:20:16 -07:00
NVShreyas
e67f4da9b5
[Perf]: Add residual, norm for nemotron_nas models (#6455) 
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
 2025-07-30 09:10:38 -07:00
Chang Liu
b4065d8ca6
[TRTLLM-6654][feat] Add support for external multimodal embeddings (#6263) 
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
 2025-07-30 10:00:15 -04:00
pcastonguay
e7ae5e2824
feat: Add support for disaggregation with pp with pytorch backend (#6369) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Signed-off-by: raayandhar <rdhar@nvidia.com>
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Signed-off-by: pcastonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: raayandhar <rdhar@nvidia.com>
Co-authored-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-07-30 09:42:13 -04:00
tomeras91
a2514d93fc
[nvbug 5380101][fix] Fix nemotronNAS loading for TP>1 (#6447) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-07-30 07:22:32 -04:00
QI JUN
2fe9cc0889
chore: remove draft_model_engine from init parameter list of PyExecutor (#6325) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-30 03:31:49 -04:00
QI JUN
1f39a11af0
chore: clean code of PyExecutor (#6445) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-30 02:11:43 -04:00
Jinyang Yuan
a427f5bece
[fix] Fix wide EP when using DeepEP with online EPLB (#6429) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-07-30 00:13:18 -04:00
peaceh-nv
5b420ad267
Rename layer to comply with deepseek (#6393) 
Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>
 2025-07-30 10:00:48 +08:00
Yechan Kim
d6eb8e2366
fix: support mixture of text & multimodal prompts (#6345) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-07-30 08:52:31 +08:00
QI JUN
13e24ab1cb
chore: remove unused code in PyExecutor (#6351) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-29 16:24:26 +08:00
nv-guomingz
49044733e1
chore: delete useless gitkeep files. (#6400) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-07-28 11:38:30 -04:00
QI JUN
4efc6496b7
chore: add _prepare_and_schedule_batch function in PyExecutor (#6365) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-28 05:50:27 -04:00
Jinyang Yuan
97f7e12588
[fix] Fix perf regression caused by MoE autotuner when using DeepEPLowLatency (#6288) 
Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com>
 2025-07-28 01:37:11 -04:00
Chang Liu
dc757799e1
[nvbugs/5401156][fix] Avoid import all models when import trtllm._common (#6266) 2025-07-27 23:29:21 -04:00
Void
f172face98
DeepEP LL dispatch FP4 (#6296) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2025-07-28 11:25:42 +08:00
Yukun He
93a0fd0a23
[TRTLLM-6445] feat: Enable AllReduce-associated fusion patterns in Llama3/4. (#6205) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-07-28 09:36:26 +08:00
YueWeng
2dd3186727
fix: remove cudaStreamSynchronize when using relaxed acceptance (#5262) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-07-28 09:18:41 +08:00
Ziyi Xiong
d853811190
[https://nvbugs/5402719][fix]: Add cuda graph dummy requests to the spec_resource_manager (#6258) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-07-26 20:32:39 -04:00
ameynaik-hub
1e5e71aa42
Mtp optimizations round1 (#5689) 
Signed-off-by: Amey Naik <212485788+ameynaik-hub@users.noreply.github.com>
Co-authored-by: Kefeng-Duan <176893526+Kefeng-Duan@users.noreply.github.com>
 2025-07-25 13:48:27 -04:00
liji-nv
e07fff4f78
[https://nvbugs/5340941] - fix: Correct custom ops used by Qwen3 Moe … (#6285) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-07-25 14:49:45 +08:00
Mike Iovine
0f2f11f90b
[TRTLLM-6453][feat] Support chunked prefill on spec decode 2 model (#6104) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-07-24 21:50:11 -04:00
Shiyu Li
375f74ecb2
[fix][nvbugs/5399355] Fix Lamport buffer clear issue for MNNVL TwoShot Allreduce and add FP16 support. (#6237) 
Signed-off-by: Shiyu Li <shili@nvidia.com>
 2025-07-25 08:01:40 +08:00
Stefan Niebler
0df758ec9f
[TRTLLM-6650][feat] Enhance beam search support with CUDA graph integration (#6217) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-07-24 18:04:41 +02:00
bhsueh_NV
7b6aadc800
[Fix][nvbug 5401163][nvbug 5404726][Qwen3] Fix bug of MoE on tp > 1 with trtllm moe backend (#6235) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-07-24 21:47:37 +08:00
liji-nv
14d94a3856
feat: Add non UB AR + Residual + Norm + Quant fusion (#6320) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-07-24 05:51:43 -04:00
Lizhi Zhou
a63a1ac7f9
[TRTLLM-6444] Add some UCX trouble shooting docs and print UCX related logs (#6085) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2025-07-24 16:21:01 +08:00
QI JUN
428e34080f
chore: remove unused variables in pyexecutor (#6280) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-24 13:16:15 +08:00
Stefan Niebler
2486eb778e
[TRTLLM-6651][feat] Enable Overlap scheduler + Beam Search in TRTLLM Sampler (#6223) 
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
 2025-07-23 12:30:50 +02:00
YueWeng
ed62a06eef
[nvbug/5322354] fix PD + MTP + overlap scheduler accuracy issue (#6136) 
Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
 2025-07-23 14:53:37 +08:00
QI JUN
a8253b942f
chore: remove duplicate should_stop_processing check (#6242) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-07-23 14:11:23 +08:00