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
4,899 Commits 28 Branches 67 Tags 2 GiB
5ff244ce54
Commit Graph

2106 Commits

Author SHA1 Message Date
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
Void
f7de285a82
[None][fix] add quantization check for DeepEP LL low precision combine in new moe comm api (#10072) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2026-01-14 22:15:29 -05:00
彭晋韬(jtao peng)
211c44b951
[None][feat] Adding torch ext API for FusedAddRMSNormQuant kernel (#9905) 
Signed-off-by: jintaop <jintaop@nvidia.com>
 2026-01-15 07:29:15 +08:00
Tzu-Ling Kan
c99faaed06
[#9760][fix] Use RequestError for validation errors to prevent engine shutdown (#9761) 
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
 2026-01-14 10:22:36 -05:00
Emma Qiao
01083b56bf
[TRTLLM-9849][infra] Update dependencies to 25.12 (#9818) 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Emma Qiao <qqiao@nvidia.com>
Signed-off-by: xxi <xxi@nvidia.com>
Signed-off-by: xxi <95731198+xxi-nv@users.noreply.github.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: xxi <xxi@nvidia.com>
Co-authored-by: xxi <95731198+xxi-nv@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2026-01-14 21:54:04 +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
Kyungmin Lee
25148d3fee
[None][feat] Support new Transformers RoPE configuration format (#10636) 
Signed-off-by: lkm2835 <lkm2835@gmail.com>
 2026-01-14 19:41:27 +09:00
xxi
e9817461ba
[None][chore] improve the readability of log for cutlass can only sup… (#10630) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-14 05:33:45 -05:00
xxi
d8862505b9
[None][chore] enable EPLB for DEEPGEMM (#10617) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-14 05:28:08 -05:00
jmydurant
e7882d5c74
[None][feat] MiniMax M2 support (#10532) 
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2026-01-14 17:38:58 +08:00
mpikulski
052c36ddd2
[TRTLLM-9522][feat] support image_embeds in OpenAI API (#9715) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2026-01-14 10:31:03 +01:00
Zhenhuan Chen
287f6c2e0f
[None][test] add log_samples and output_path for trtllm_eval (#10629) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2026-01-14 16:01:38 +08:00
Yukun He
15281de799
[None][fix] Reduce host overhead for unified nvfp4 gemm tuning path. (#10503) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-14 14:26:18 +08:00
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
Leslie Fang
795e690bca
[https://nvbugs/5753788][chore] Padding empty chunk for configurable moe (#10451) 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
 2026-01-14 10:42:17 +08:00
Yuxian Qiu
d3f4fbb742
[None][fix] Avoid write-write race for async pp send. (#10488) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-14 09:39:36 +08:00
Yuxian Qiu
2acd03030a
[https://nvbugs/5781589][fix] Implement pp skip forward for all spec workers. (#10578) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-14 09:36:35 +08:00
Balaram Buddharaju
ccdfa43a6e
[https://nvbugs/5791900][fix] Fix HelixCpMnnvlMemory init with PP (#10533) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-13 15:48:42 -05:00
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
benzh-2025
6df2c8a074
[None][feat] add fp4 gemm + allreduce (#9729) 
Signed-off-by: benzh 
Signed-off-by: benzh-2025
 2026-01-13 21:11:13 +08:00
Tailing Yuan
38296a472b
[None][feat] Layer-wise benchmarks: make model init more general and support weights loading (#10562) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2026-01-13 19:17:03 +08:00
Void
7d16f3a28b
[https://nvbugs/5788127][fix] Use uint64_t as the dtype of lamport_buffer_size to avoid overflow (#10499) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
 2026-01-13 17:16:22 +08:00
Guoming Zhang
bdaee87895
[TRTLLM-10060][feat] Enable attention dp for Nemotron Super v3. (#10347) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2026-01-13 17:13:55 +08:00
JunyiXu-nv
e291a834db
[TRTLLM-8462][feat] Support GET/DELETE v1/responses/{response_id} (#9937) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2026-01-13 03:57:14 -05:00
Yuxian Qiu
04b112651b
[None][feat] Hang detection for executor loop and worker. (#10480) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-13 02:34:32 -05:00
xxi
ba1037ca4a
[https://nvbugs/5762336][fix] support to parse the keyword modules_to_not_convert of the HF model config" (#10527) 
Signed-off-by: xxi <xxi@nvidia.com>
 2026-01-12 20:21:01 -05:00
Iman Tabrizian
48b09e5a25
[https://nvbugs/5689235][fix] Fix cancellation+chunked prefill+disagg (#10111) 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
 2026-01-12 18:23:26 -05:00
Gal Hubara-Agam
18a33764b5
[None][chore] Print correct backend name in benchmark report (#10597) 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
 2026-01-12 14:46:00 -05:00
Xianjie Qiao
3a9a00b544
[None][feat] Add ExpertStatistic and DUMMY_ALLREDUCE for configurable_moe (#10401) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2026-01-12 14:10:31 +08:00
Yechan Kim
8e0d20d901
[TRTLLM-10195][feat] K-EXAONE support (#10355) 
Signed-off-by: Jaedeok Kim <jaedeokk@nvidia.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: Jaedeok Kim <jaedeokk@nvidia.com>
 2026-01-12 00:29:51 +09:00
Faraz
fdbdbba540
[https://nvbugs/5752687][fix] Choose register model config over root config for VLM (#10553) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2026-01-09 12:10:52 -05:00
Yechan Kim
7295af68ba
[None][fix] Enable AttentionDP on Qwen3-VL and fix test (#10435) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2026-01-10 00:13:26 +09:00
Kaiyu Xie
1c69aad850
[TRTLLM-10309] [feat] Optimize qk rope/nope concat for DSA (#10571) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2026-01-09 09:50:57 -05:00
Yuxian Qiu
80f261ea36
[https://nvbugs/5622938][feat] Run sample_async on extra stream. (#10215) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-09 18:15:18 +08:00
Chang Liu
78bb245554
[https://nvbugs/5787453][fix] Better align MLA chunking with indexer chunking when chunked prefill enabled for DSV32 (#10552) 2026-01-09 00:49:39 -08:00
JadoTu
4c498bfe58
[TRTLLM-9676][fix] Fix mamba_cache_manager when enabling cuda_graph_padding and let test cover this case (#9873) 
Signed-off-by: JadoTu <107457950+JadoTu@users.noreply.github.com>
 2026-01-09 14:50:16 +08:00
Yuxian Qiu
afa55c12b6
[None][fix] revert https://github.com/NVIDIA/TensorRT-LLM/pull/10445. (#10547) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2026-01-08 21:50:04 -05:00
Mike Iovine
4092a87b6f
[https://nvbugs/5740075][fix] Fix sm120 speculation (#10049) 
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2026-01-08 19:55:43 -05:00
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
mpikulski
e0331297a6
[TRTLLM-9522][fix] broken cast (#9975) 
Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>
 2026-01-08 06:47:39 -05:00
William Zhang
c0ae6bbdbe
[None][feat] EPD for Qwen3 VL (#10470) 
* Why?

We would like to support EPD disaggregated serving for Qwen3 VL.

* What?

This commit adds such support, and extends existing unit tests for
correctness checks.

Some minor (protected) interface changes had to be made to the
weight mapper as a side-effect.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2026-01-08 06:45:54 -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
bhsueh_NV
bea61bb17d
[None][fix] Mistral large 3 few code refine (#10405) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2026-01-08 06:38:49 -05:00
Yiqing Yan
dc6b743fb6
[None][chore] Bump version to 1.2.0rc8 (#10542) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2026-01-08 04:51:44 -05:00
Yukun He
09d9878385
[TRTLLM-9661][chore] Further reduce tuning time for cuteDSL nvFP4 dense gemm. (#10339) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-08 10:21:02 +08:00
Ziyi Xiong
7187afe7b9
[https://nvbugs/5781589][fix] Skip spec dec for non-last rank (#10445) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2026-01-07 13:55:45 -05:00
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
Kanghwan
dc32bac9fc
[#4745][fix] Pass lora_params through Qwen2/3 model forward (#10174) 
Signed-off-by: Kanghwan Jang <861393+karljang@users.noreply.github.com>
 2026-01-07 15:30:17 +08:00
Fanrong Li
a34aa63685
[https://nvbugs/5767223][feat] add pp support for DeepSeek-v3.2 (#10449) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-07 12:29:51 +08:00
Zongfei Jing
bb2f883296
[None] [feat] Add test script and raster M for gather fc1 kernel (#10429) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2026-01-07 09:31:49 +08:00
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
Lizhi Zhou
6a4bebcd01
[None][chore] remove redundant retries while binding to arbitrary port (#10452) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-06 10:39:15 -05:00
Kaiyu Xie
2eaabd7461
[None] [fix] Fix undefined tokens_per_block (#10438) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2026-01-06 02:42:37 -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
Xiao Xuan
46f035befe
[#2511][fix] eagle: qwen2 capture hidden states (#10091) 
Signed-off-by: SpicyNoodle <522169030@qq.com>
 2026-01-05 21:46:41 -05:00
alel
6b8ae6fa81
[None][feat] CuteDSL MOE FC1 Enhancement (#10088) 
Signed-off-by: Yuhan Li <51736452+liyuhannnnn@users.noreply.github.com>
 2026-01-06 09:30:43 +08:00
JadoTu
82aaf98070
[None][feat] add the eos tokens in generation config to stop words in the sampler (#10389) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2026-01-06 09:24:03 +08:00
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
Mike Iovine
db2614ef10
[https://nvbugs/5772414][fix] Fix draft token tree depth=1 corner case (#10385) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-05 17:20:14 +01:00
Mike Iovine
bedfff4f00
[https://nvbugs/5772521][fix] Fix draft token tree chain crash (#10386) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2026-01-05 17:18:44 +01:00
Anthony Chang
225d3a9001
[None][perf] TRTLLM MoE maps to lower tuning buckets when ep>1 (#9998) 
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
 2026-01-05 17:16:12 +01:00
Balaram Buddharaju
a792c23dcf
[TRTLLM-9465][fix] Swap TP-CP grouping order (#10350) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-05 20:08:03 +08:00
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
Fanrong Li
4931c5eb3a
[None][feat] update deepgemm to the DeepGEMM/nv_dev branch (#9898) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-05 16:43:42 +08:00
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
HuiGao-NV
2f768b76f8
[https://nvbugs/5715568][fix] Force release torch memory when LLM is destroyed (#10314) 
Signed-off-by: Hui Gao <huig@nvidia.com>
 2026-01-05 15:30:18 +08:00
Pengyun Lin
c04cf4334e
[TRTLLM-8242][feat] Add stability tags for serve subcommand (#10012) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2026-01-05 14:16:15 +08:00
Yukun He
0937df2c68
[TRTLLM-10185][feat] AutoTuner Cache: Support cache file lock and merge all ranks into one (#10336) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2026-01-05 13:44:09 +08:00
Tailing Yuan
a7fe043b13
[None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2026-01-05 11:23:04 +08:00
Cheng Hang
656c705ff1
[None][feat] sm100 weight-only kernel (#10190) 
Signed-off-by: Cheng Hang <chang@nvidia.com>
 2026-01-05 09:44:36 +08:00
Fanrong Li
b5a1e10bc0
[https://nvbugs/5779534][fix] fix buffer reuse for CUDA graph attention metadata (#10393) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2026-01-05 09:43:44 +08:00
Wanli Jiang
da0830670a
[TRTLLM-10065][feat] Add accuracy tests for super-v3 with multiple-gpus (#10234) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2026-01-05 09:41:49 +08:00
Lizhi Zhou
82c1ba84a7
[https://nvbugs/5649010][fix] use 0 port as arbitrary port when disagg service discovery is enabled (#10383) 
Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com>
 2026-01-05 09:40:40 +08:00
bhsueh_NV
0517b62789
[https://nvbugs/5772363][fix] fix bug of Mistral-Small-3.1-24B-Instruct-2503 (#10394) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2026-01-05 09:04:13 +08:00
Faraz
8e2065b4d9
[https://nvbugs/5670469][fix] Filter 0s and choose min of kv_head for Nemotron model (#10206) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2026-01-05 08:42:53 +08:00
dongfengy
afc533193d
[None][feat] Support nvfp4 for gptoss (#8956) 
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
 2026-01-04 08:57:44 -05:00
Jaedeok Kim
a4dcc6a711
[TRTLLM-10171][fix] Correct attention handling in ModelConfig and KVCacheManager (#10330) 
Signed-off-by: Jaedeok Kim <jaedeokk@nvidia.com>
 2026-01-04 06:07:30 -05:00
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
Izzy Putterman
bdf6953ddc
[None][feat] Eagle: MLA Based Eagle (#9677) 
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
 2026-01-02 13:45:07 -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
Balaram Buddharaju
4a1b742aa0
[TRTLLM-9467][fix] Fix PP+CP combination with helix parallelism (#10312) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2026-01-01 13:42:53 -05:00
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
Mike Iovine
9085021aa4
[None][feat] Implement sampling for MTP 1-model (#10019) 
Signed-off-by: Mike Iovine <miovine@nvidia.com>
 2025-12-31 13:48:34 -05:00
Simeng Liu
84d107b2f0
[https://nvbugs/5717993][fix] Add execution_stream across PyExecutor, KVCacheManager, PeftCacheManager to ensure proper CUDA stream synchronization between KV cache transfer operations and model forward kernels. (#10060) 
Signed-off-by: SimengLiu-nv <simengl@nvidia.com>
 2025-12-31 09:22:54 -08:00
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
Jin Li
ef1d4a40b5
[https://nvbugs/5727475][fix] Avoid use property with setter in nn.Mo… (#10212) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-31 06:21:36 -05:00
Necofish
73870ae4ad
[None][feat] support Qwen3-VL dense model in pytorch backend (#9060) 
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
 2025-12-31 17:54:26 +09:00
Pengyun Lin
fad000589d
[None][chore] Unify DS tool parser names (#10239) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-31 14:40:07 +08:00
Jin Li
34c2fd50a9
[https://nvbugs/5707359][fix] Unwaive OOM case that should be fixed by #9446 (#10334) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-31 10:41:39 +08:00
Yuxian Qiu
1f3afb8e6f
[None][feat] Implement send_object for TorchDist. (#10213) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-31 10:40:52 +08:00
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
Bo Li
1f0365da36
[None][infra] Add LongBenchV1 to trtllm-eval. (#10265) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
 2025-12-30 21:39:34 +08:00
binghanc
692d8f2023
[TRTLLM-9455][feat] support for new checkpoint (#10082) 
Signed-off-by: binghanc <176802681+binghanc@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-12-30 14:46:39 +08:00
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
Ziyi Xiong
c59aa8bec5
[TRTLLM-9962][feat] Some optimizations for two-model spec dec (#10208) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-28 12:52:04 +08:00
JunyiXu-nv
55bc6a5ff8
[https://nvbugs/5753250][fix] Fix undefined local variable in responses utils (#10154) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
Signed-off-by: JunyiXu-nv <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-28 06:59:32 +08:00
shivghai
ee07a7c55e
[None][fix] [Gemma3] Fix RoPE for local attention for Gemma3 (#9961) 
Signed-off-by: Shiv Ghai <8965168+shivghai@users.noreply.github.com>
 2025-12-27 11:50:59 -08:00
Guoming Zhang
1865020b6f
[TRTLLM-8577][feat] Clean the Qwen3-next code by removing Qwen3NextCo… (#10228) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
 2025-12-27 22:49:55 +08:00
Olya Kozlova
55f3cda66d
[None][fix] Fix request_id for best_of/n case (#8368) 
Signed-off-by: Olya Kozlova <okozlova@nvidia.com>
 2025-12-26 22:20:24 +01:00
Jin Li
c04563657e
[TRTLLM-7735][feat] Attention NVFP4 out support for torch compile (#9740) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-27 00:07:20 +08:00
Pengyun Lin
c5b0f9e436
[https://nvbugs/5633700][fix] Cache tiktoken vocab for gpt-oss (#10219) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-26 18:39:03 +08:00
Wanli Jiang
14554ab3f3
[None][feat] Support multi-gpu running for nemotron-v3-nano and super (#10118) 
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
 2025-12-26 11:23:14 +08:00
Enwei Zhu
13ffe52ad0
[None][fix] Allow YAML config overwriting CLI args for trtllm-eval (#10296) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-25 15:08:15 -05:00
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
bhsueh_NV
db3430f589
[None][feat] Support VLM part for Mistral Large 3 (#10188) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-12-25 11:20:58 -05:00
Jin Li
7e4cef9def
[None][fix] Cherry-pick conflict changes for PR 7999 PR 8515 (#9446) 
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
 2025-12-25 10:23:04 -05:00
Ziyi Xiong
d8b5aeb061
[https://nvbugs/5652062][fix] Rewind kv_cache and reset draft tokens (#10160) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-25 09:13:51 -05:00
ZhichenJiang
46e4af5688
[TRTLLM-9831][perf] Enable 2CTA with autotune for CuteDSL MoE and Grouped GEMM optimizations (#10201) 
Signed-off-by: zhichen jiang <zhichenj@NVIDIA.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-25 09:04:20 -05:00
Zhenhuan Chen
8462cf6c96
[TRTLLM-9578][feat] make PDL enabled by default (#9695) 
Signed-off-by: Zhenhuan Chen <zhenhuanc@nvidia.com>
 2025-12-25 07:15:24 -05:00
Xianjie Qiao
53b81783b1
[None][fix] Fix pageable H2D memcopy issue on GB200 (#10289) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2025-12-25 18:15:57 +08:00
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
Ziyi Xiong
43178590d1
[TRTLLM-10143][feat] Reuse previous draft requests if possible (#10263) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-24 17:48:38 -08:00
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
Necofish
8614cd3439
[None][fix] fix: resolve GPU memory imbalance in concurrent weight loading (#6472) 
Signed-off-by: Necofish <liuxiangyang@mail.ustc.edu.cn>
Signed-off-by: Nekofish-L <liuxiangyang@mail.ustc.edu.cn>
Signed-off-by: Jie Li <lijie@nvidia.com>
Co-authored-by: Jie Li <lijie@nvidia.com>
 2025-12-24 09:43:09 -05:00
Suyog Gupta
e2891a6c77
[#10052][feat] AutoDeploy enable cudagraphs for flashinfer BatchDecode (#10193) 
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: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
 2025-12-24 05:55:09 -08:00
shuyixiong
f4f0fe85e9
[TRTLLM-9737][chore] Add rl perf reproduce script and enhance the robustness of Ray tests (#9939) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-12-24 15:27:01 +08:00
Yukun He
595daa5089
[TRTLLM-9615][feat] Support synchronization through PP ranks in the distributed tuning system (#10011) 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-12-24 15:03:10 +08:00
Fanrong Li
156f6453dc
[TRTLLM-9798][feat] Change to use new DeepGEMM MQA sm100 kernel for MTP-3 (#10226) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-24 14:39:12 +08:00
Balaram Buddharaju
8c1cfc872b
[TRTLLM-9493][feat] Custom AllToAll for helix parallelism (#9986) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-23 18:14:30 -08:00
Grzegorz Kwasniewski
06900a7f19
[TRTLLM-9565][fix] Fix deepseek sharding (#9984) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-12-23 10:28:14 -05:00
Xianjie Qiao
871c6b435c
[None] [feat] skip batch_tokenize_prompts in CustomDataset (#10214) 
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2025-12-23 17:40:57 +08:00
Yiqing Yan
59b05dc0a8
[None][chore] Bump version to 1.2.0rc7 (#10216) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-12-23 15:07:47 +08:00
Harshini Komali
d691371eaf
[TRTLLM-9091] [feat] Replace GenAI-Perf with AIPerf (#9310) 
Signed-off-by: lkomali <lkomali@nvidia.com>
Signed-off-by: Harshini Komali <157742537+lkomali@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-12-23 13:25:55 +08:00
Li Min
1e82ff7a0c
[TRTLLM-9989][fix] Fix tvm_ffi aaarch64 issue. (#10199) 
Signed-off-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
 2025-12-23 10:20:40 +08:00
Yuxian Qiu
696f754ef4
[None][fix] avoid implicit cudaStreamSynchronize in sample_async. (#10120) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-23 10:15:40 +08:00
Tailing Yuan
648196f8ae
[TRTLLM-9432][feat] Reduce synchronization and recompilation for qwen3-next (#9691) 
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
 2025-12-23 10:14:29 +08:00
Faraz
f05af48bca
[https://nvbugs/5747674][fix] Add contiguous() before view() in load_expert_w3_w1_weight and load (#10136) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2025-12-22 21:03:34 -05:00
Fanrong Li
0d2500c631
[TRTLLM-9677][feat] Support DeepSeek-V3.2 tool parser (#10126) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-23 08:46:47 +08:00
Grzegorz Kwasniewski
ccc64da287
[TRTLLM-9847][fix] WAR fix hanging fused allreduce. (#10087) 
Signed-off-by: greg-kwasniewski1 <213329731+greg-kwasniewski1@users.noreply.github.com>
 2025-12-23 00:03:32 +01:00
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
JunyiXu-nv
aaa87abf41
[TRTLLM-7906][feat] Support multiple post process for Responses API (#9908) 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
 2025-12-22 11:33:34 -05:00
William Zhang
a6a88985cf
[TRTLLM-9409][feat] Pass MRoPE tensors for EPD disagg (#9758) 
* Why?

Certain VLMs like the Qwen family need more than just the multimodal
embeddings in the language model, and need MRoPE position IDs and
deltas. Prior to this commit, only the embeddings could be communicated
from the encoder worker to the prefill worker.

* What?

This commit extends the `DisaggregatedParams` to include the MRoPE
information. It also adjusts several pieces of code required to
communicate that between E, P and D workers.

Closes TRTLLM-9409.

Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
 2025-12-22 06:32:49 -05:00
Yan Chunwei
ea6cd76c55
[None][refactor] simplify get_stats and get_kvcache_events with rpc (#9980) 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-12-22 18:23:43 +08:00
JadoTu
7421224d69
[None][fix] NVFP4 linear method's weight and weight_scale padding (#10148) 
Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
 2025-12-22 15:00:31 +08:00
Fanrong Li
f0bd60a395
[https://nvbugs/5684820][fix] fix the detokenizer issue for DeepSeek-v3.2 (#10106) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-12-22 10:56:33 +08:00
Balaram Buddharaju
5266475014
[None][feat] Cudagraph updates for helix parallelism (#10141) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-12-21 15:21:52 -05:00
shuyixiong
4fc6036276
[https://nvbugs/5702793][fix] Fix view operation on uncontiguous tensor (#10147) 
Signed-off-by: Shuyi Xiong <219646547+shuyixiong@users.noreply.github.com>
 2025-12-21 11:47:20 -05:00
bhsueh_NV
cd4b4f43fa
[None][feat] Support Eagle3 on Mistral Large3 (#9971) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-12-21 10:25:45 -05:00
xxi
5ae154022a
[TRTLLM-9872][fix] clear the failed test at CI when enalbe_configurab… (#10067) 
Signed-off-by: xxi <xxi@nvidia.com>
 2025-12-21 08:14:50 -05:00
Bo Li
a66eeab537
[TRTLLM-9805][feat] Skip Softmax Attention. (#9821) 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
 2025-12-21 02:52:42 -05:00
Enwei Zhu
21a93fbf9d
[TRTLLM-9992][perf] Enable PDL for CuteDSL kernels and overlap MoeOutputMemset (#10043) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-12-20 03:12:41 -05:00
Yuxian Qiu
e75331480f
[None][fix] fix draft_lengths for CUDA graph capture. (#10004) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-12-20 09:04:48 +08:00
Pengyun Lin
ac03915dc3
[TRTLLM-9604][feat] DS R1 & V3.1 tool parser (#10010) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-12-19 17:20:03 +08:00
Chang Liu
31bc14b350
[TRTLLM-9654][feat] Support DeepSeek-V32 chat template (#9814) 
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
 2025-12-19 17:05:38 +08:00
Ziyi Xiong
70b4d282c6
[TRTLLM-7736][feat] Incrementally update the inputs of target and draft models (#9708) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
 2025-12-19 15:11:25 +08:00
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