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
1,530 Commits 25 Branches 59 Tags 2.1 GiB
release/0.21
Commit Graph

285 Commits

Author SHA1 Message Date
Zhenhuan Chen
e70a205dab
[TRTLLM-4638] feat(scaffolding): update Reward Controller to PRM specific controller with step split (#4337) 
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-05-19 17:53:41 +08:00
Yuxian Qiu
cf6cd940e5
feat: Add pp support for hybrid attn/mamba model (#4358) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-19 14:47:45 +08:00
Netanel Haber
9cd8148f28
API Breaking Change + Readability: "decoder"->"sampler" (#4121) 
* *decoder*->*sampler*; new_tensors_device: dict[str, torch.Tensor] -> device: SampleStateTensors

* **Breaking Change**, as it changes public interfaces, main changes:
* PyTorchConfig [consumed via LLM(pytorch_backend_config)]: Configuration parameters mixed_decoder and enable_trtllm_decoder -> sampler.
* Command-line argument --enable_trtllm_decoder becomes --enable_trtllm_sampler in examples/pytorch/quickstart_advanced.py.

---------

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2025-05-16 23:52:25 +08:00
Lucas Liebenwein
8e4320ede5
[AutoDeploy] configurable cache resize (#4372) 
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-05-16 10:07:09 -04:00
Daniel Cámpora
df19430629
chore: Mass Integration 0.19 (#4255) 
* fix: Fix/fused moe 0.19 (#3799)

* fix bug of stream init

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* fix bug

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

---------

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* fix: Add pre-download of checkpoint before benchmark. (#3772)

* Add pre-download of checkpoint before benchmark.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Add missing remote code flag.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Move from_pretrained to throughput benchmark.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Move download and use snapshot_download.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Removed trusted flag.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Fix benchmark command in iteration log test.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

---------

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* [https://nvbugspro.nvidia.com/bug/5241495][fix] CUDA Graph padding with overlap scheduler (#3839)

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fuse

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* TRTLLM-4875 feat: Add version switcher to doc (#3871)

Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

* waive a test (#3897)

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* docs:fix https://nvbugs/5244616 by removing new invalid links. (#3939)

Signed-off-by: nv-guomingz <37257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: nv-guomingz <37257613+nv-guomingz@users.noreply.github.com>

* fix: remote mpi session abort (#3884)

* fix remote mpi session

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* fix

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

---------

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* skip fp8 gemm for pre-hopper (#3931)

Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>

* [https://nvbugspro.nvidia.com/bug/5247148][fix] Attention DP with overlap scheduler (#3975)

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* update multigpu list

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix namings

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* Doc: Fix H200 DeepSeek R1 perf doc (#4006)

* fix doc

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>

* update perf number

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>

---------

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>

* Fix the perf regression caused by insufficient cache warmup. (#4042)

Force tuning up to 8192 sequence length for NVFP4 linear op. Also, make this runtime-selectable with UB enabled.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>

* doc: Update 0.19.0 release notes (#3976)

Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

* Optimize the AutoTuner cache access code to reduce host code overhead. (#4060)

The NVFP4 Linear op is very sensitive to the host overhead.
This PR introduces customizable `find_nearest_profile` and `get_cache_key_specifc`, which allow users to override the default method for generating the cache key.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>

* Update switcher (#4098)

Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

* doc: update release notes (#4108)

Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

* docs:update 0.19 doc. (#4120)

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

* docs:add torch flow supported model list. (#4129)

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

* doc: Release V0.19 Perf Overview Update (#4166)

Signed-off-by: zpatel <22306219+zbpatel@users.noreply.github.com>

* Fix readme of autodeploy.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update tensorrt_llm/_torch/pyexecutor/llm_request.py

Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>

* Revert mgmn worker node.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Change to disable_overlap_scheduler.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

---------

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
Signed-off-by: nv-guomingz <37257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: zpatel <22306219+zbpatel@users.noreply.github.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
Co-authored-by: bhsueh_NV <11360707+byshiue@users.noreply.github.com>
Co-authored-by: Frank <3429989+FrankD412@users.noreply.github.com>
Co-authored-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
Co-authored-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Co-authored-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: nv-guomingz <37257613+nv-guomingz@users.noreply.github.com>
Co-authored-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Co-authored-by: Zac Patel <22306219+zbpatel@users.noreply.github.com>
 2025-05-16 10:53:25 +02:00
Barry Kang
0e14941b7f
[fix] Fixed incorrect mixed precision MoE conversion (#4351) 
Fix for mixed precision MoE conversion

Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-05-16 13:43:41 +08:00
WeiHaocheng
54d28718c7
feat: support benchmark on scaffolding (#3328) (#4286) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
 2025-05-16 12:28:49 +08:00
Suyog Gupta
b0f7522c82
[AutoDeploy]feat: Add an AutoDeploy compile backend that only calls torch.compile (#4240) 
* add a torch-compile backend

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* readme changes

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* plumb torch-compile through build_and_run_ad.py

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* plumb torch-compile through build_and_run_ad.py

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* plumb torch-compile through build_and_run_ad.py

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* add torch-cudagraph backend

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* update readme

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* update readme

Signed-off-by: Suyog Gupta <41447211+suyoggupta@users.noreply.github.com>

* further enhanced compiler backends

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* further enhance readme

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* better specified defaults in simple_config.py

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* fix typo in simple_config.py

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* updated deepseek-v3 support

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* revert accidental deletion in AD Readme

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

---------

Signed-off-by: Suyog Gupta <41447211+suyoggupta@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>
 2025-05-16 08:38:15 +08:00
Yechan Kim
c6e2111f4e
feat: enhance trtllm serve multimodal (#3757) 
* feat: enhance trtllm serve multimodal

1. made the load_image and load_video asynchronous
2. add image_encoded input support to be compatible with genai-perf
3. support text-only on multimodal mdoels(currently, Qwen2-VL & Qwen2.5-VL)

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* add test

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix bandit

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* trimming uils

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* trimming for test

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* genai perf command fix

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* command fix

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* refactor chat_utils

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* stress test genai-perf command

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

---------

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-05-15 16:16:31 -07:00
yuxianq
4f8afe4cc6
feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-16 04:16:53 +08:00
yuxianq
0e87fcc228
refactor: use x is None instead of x == None. (#4244) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-15 20:00:04 +08:00
zhhuang-nv
97bc680cd8
feat: support kv cache reuse for MLA (#3571) 
* support kv cache reuse for MLA

load compressed_kv and k_pe and do up-projection
use 192/128 head size MLA context kernel
support Blackwell and Hopper now

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* add CI test

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix: set k_pe head_num to 1 for kernel 2 and kernel 2V2

Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>

* resolve comments

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* use GPTJ style RoPE for MLA

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix rebase error and some docs

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix kv_lens

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* tiny fix

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix torch compile

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix: use normal device memory instead of pinned memory for unit test

Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>

* fix L0 tests

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* fix torch compile after rebase

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* resolve comments

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

* resolve comments again

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>

---------

Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
Signed-off-by: zhhuang-nv <145532724+zhhuang-nv@users.noreply.github.com>
Co-authored-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2025-05-15 15:22:21 +08:00
Kaiyu Xie
b4e5df0ee0
Breaking change: perf: Enable scheduling overlap by default (#4174) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-05-15 14:27:36 +08:00
dominicshanshan
404fbe9b32
[https://nvbugs/5277113][fix]genai-perf API change stress test (#4300) 
* fix bug 5277113.

Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

* fix bug 5277113 and 5278517.

Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

---------

Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
 2025-05-15 14:12:34 +08:00
Simeng Liu
efe0972efb
doc: Add tensorrtllm_backend serving documentation in the Deepseek-V3 README (#4338) 
Add tensorrtllm_backend serving option in the Deepseek-V3 README

Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2025-05-15 09:31:28 +08:00
Kaiyu Xie
6c45586c51
chore: Remove deprecated Python runtime benchmark (#4171) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-05-14 18:41:05 +08:00
Barry Kang
20b42912ce
[TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123) 
Support DeepSeek-R1 W4A8 on Hopper

Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Co-authored-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-05-14 15:48:07 +08:00
brb-nv
8280c3d4f2
feat: Support Gemma3-1b-it in Pytorch workflow (#3999) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-05-14 14:02:44 +08:00
Zhanrui Sun
23b9705bf4
chore: bump version to 0.20.0rc3 (#4261) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-05-14 10:15:25 +08:00
brb-nv
cd5b3d21a0
feat: Support Mistral Small 3.1 24B VLM in TRT workflow (#4183) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-05-14 03:47:22 +08:00
bhsueh_NV
24be357964
doc: update qwen3 document (#4246) 
* update qwen3 document

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* remove wrong note

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

---------

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-05-13 11:05:47 +08:00
Yechan Kim
3e9bda3a09
[feat] Support HyperCLOVAX-SEED-Text language part (#3902) 
* feat: support HyperCLOVAX-SEED-Text language part

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* add Pytorch flow and remove test file

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* revert summarize

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix summarize

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* remove from pytorch example

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

---------

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
 2025-05-12 16:05:14 +08:00
Zhenhuan Chen
9212e9a740
[TRTLLM-4911] feat(scaffolding): make sampling_params only setable by controller (#4151) 
feat(scaffolding): make sampling_params only setable by controller

Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-05-12 15:29:09 +08:00
xinhe-nv
186e2b8c38
[TRTQA-2802][fix]: add --host for mgmn serve examples script (#4175) 
remove prepare data

Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-05-12 13:28:42 +08:00
mayani-nv
fe3a993234
chore: PR to fix the formatting errors (#4200) 
* updating the run_dtm_pld.py to handle logits correctly

* following correct code formatting

* Update run_dtm_pld.py to account for correct code formatting

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>

* correct formatting for the multimodal README PR

---------

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: Ubuntu <Azureuser@mayani-nch100-vm1.42fmcfe2wyrepoque0x2bs4uue.jx.internal.cloudapp.net>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-05-09 16:31:36 -07:00
mayani-nv
5c1c69cf9c
fix: draft target README and assertion for logits-based acceptance (#4167) 
* updating the run_dtm_pld.py to handle logits correctly

* following correct code formatting

* Update run_dtm_pld.py to account for correct code formatting

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>

---------

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: Ubuntu <Azureuser@mayani-nch100-vm1.42fmcfe2wyrepoque0x2bs4uue.jx.internal.cloudapp.net>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-05-09 16:08:47 -07:00
mayani-nv
25533a7736
Updating the multimodal models README to add steps for running phi-4-multimodal instruct (#3932) 
* Update run.py for draft_target_model

This change makes the draft target model works without mismatch in the vocab size 

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>

* updating README with phi-4-multimodal-instruct steps

* adding ENGINE_DIR, HF_DIR and CKPT_DIR as per review

* addressing review comments on PR

* updating readme

---------

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: rakib-hasan <rhasan@nvidia.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-05-09 15:42:58 -07:00
WeiHaocheng
0f01826dde
feat: support task collection for to collect information (#3328) (#3824) 
Signed-off-by: fredw (generated by with_the_same_user script) <20514172+WeiHaocheng@users.noreply.github.com>
 2025-05-09 17:09:01 +08:00
Yi Zhang
91bf5e6a8e
[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 
Add Piecewise CUDA Graph Support

Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
 2025-05-09 11:04:01 +08:00
shaharmor98
7d94c9561f
feat: support multi lora adapters and TP (#3885) 
* support multi lora, tp

Signed-off-by: Shahar Mor <17088876+shaharmor98@users.noreply.github.com>
 2025-05-08 23:45:45 +08:00
Enwei Zhu
74df12bbaa
[TRTLLM-4480][doc] Documentation for new accuracy test suite and trtllm-eval (#3946) 
* fix formula

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* update doc

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* 1st version

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* polish

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-05-08 19:35:23 +08:00
Yan Chunwei
389614ca99
chore: remove data stage in serve example on slurm (#4138) 
Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-05-08 11:18:56 +08:00
Ivy Zhang
d7c51c953b
test: add INTEGRATION_TEST env var to speed up integration test (#3618) 
add INTEGRATION_TEST env var

Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
 2025-05-08 10:44:50 +08:00
Yan Chunwei
0c26059703
chore: Cleanup deprecated APIs from LLM-API (part 1/2) (#3732) 
* beam_width and max_new_token

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* remove beam_width

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* remove min_length

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

* remove return_num_sequences

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>

---------

Signed-off-by: Superjomn <328693+Superjomn@users.noreply.github.com>
 2025-05-07 13:20:25 +08:00
Enwei Zhu
c28b90984f
[TRTLLM-3925, https://nvbugs/5245262] [fix] Normalize LLM.generate API (#3985) 
* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-05-07 11:06:23 +08:00
Chuang Zhu
09a28becae
fix cache buffer (#3942) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-05-07 09:49:44 +08:00
bhsueh_NV
5c0f554b9e
doc: update qwen3 document (#4073) 
* update qwen3 document

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

* remove useless codes

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>

---------

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-05-06 08:42:51 +08:00
pansicheng
e84dc6b3c7
feat: add deepseek-r1 reasoning parser to trtllm-serve (#3354) 
* add deepseek-r1 reasoning parser

Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>

* fix test

Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>

---------

Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
Co-authored-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-05-06 08:13:04 +08:00
yuxianq
2cfcdbefee
feat: run mmlu and summarize without engine_dir. (#4056) 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
 2025-05-05 19:35:07 +08:00
Yechan Kim
061a6209b5
fix: [nvbug/5252057] Fix kv cache reuse on PyTorch multimodal (#4025) 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
 2025-05-02 10:53:06 -07:00
bhsueh_NV
561ee44737
add ci and doc for qwen3 (#4022) 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-05-02 14:13:38 +08:00
Lucas Liebenwein
be916b19e0
feat: [AutoDeploy] unfusing attention for native support (#3668) 
* [AutoDeploy] unfused streamlined attention + caching

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* improved unit testing

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* reviewer feedback

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* some updates to attn_mask handling

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* updated manual benchmarking and cudagraph capture

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

---------

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-05-02 09:06:49 +08:00
Erin
8fe7bdeacf
feat: LogitsProcessor in PyTorch backend (#3145) 
* support lp in pytorch backend

Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>

* fix tp

Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>

---------

Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
 2025-05-01 14:15:30 -07:00
YueWeng
b1621e8d4e
feat: add relaxed acceptance for DS (#3865) 
* add relaxed acceptance for DS R1

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>

* clean and update docs

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>

* fix

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>

* Modified based on review

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>

* fix mtp manager issue

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>

---------

Signed-off-by: Yue Weng <25103990+yweng0828@users.noreply.github.com>
Co-authored-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-05-01 21:50:36 +08:00
Zhanrui Sun
86e7474a9b
chore: bump version to 0.20.0rc2 (#3949) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-30 11:44:43 +08:00
Dom Brown
8709fe8b53
chore: bump version to 0.19.0 (#3598) (#3841) 
test: add test cases for 0.19 release (#3608)

* fix test name



* add quickstart test for nemotron-ultra



* add rcca multi-node test case for deepseek-v3



* add rcca info



---------




squash (#3642)



fix: nvbugs/5187237: fix deterministic mode crash (#3448)

* nvbugs/5187237 nvbugs/5112075: fix deterministic mode error

* remove waive


* Revert "remove waive"

This reverts commit 0bf5486d19906d692bfb7a6262333c296b0087ac.



* revert ar fusion



---------



update fp8 doc (#3647)




tests: change qa perf test to trtllm-bench (#3619)




 fix: FP8 quantized lm_head (NvBug 5214229) (#3567)



infra: Add PR approval protection for the release branch (#3634)



fix: nvbugs/5231298: pytorch allreduce issue (#3673)



Fix: nvbugs/5222698 variable not defined (#3630)

* Fix: nvbugs/5222698 variable not defined



* Tidy code



---------



test:sync waives.txt from main branch by disabling test_perf/gpt_350m-cppmanager case (#3685)



test:restore fp8 kv cache testing for L0 (#3671)



doc: Update DeepSeek perf docs (#3693)

* Update DeepSeek perf docs



* update



* Apply suggestions from code review




---------




tests: waive test_llm_multi_node (#3664)



fix: update test_user_buffers_mm_add_prologue atol (#3711)



Fix: cherry-pick hmac encryption from main branch (#3635)

* security fix cherry-pick changes from main



* fix hmac in remote mpi session (#3649)



---------





Un-waive DS-V3-Lite tests. (#3621)



fix: FP8 kv accuracy (#3675)

* fix FP8 kv accuracy



* update doc



---------



Fix script options for engines. (#3622)



unwaive multi-node test (#3721)



chore : Split more tests out of gpt tests (#3524) (#3674)



doc:add torch examples link into torch backend documentation (#3749)




test: Get Eagle tests working (#3593) (#3722)




Waive L0 test (#3756)



waive failed case in perf test, change default max_batch_size to 512 and write config.json to output log (#3656)





Update ds v3 parameters in stress test. (#3676)

waive gemma on L20 (#3766)



https://nvbugs/5141291: Fix convert.py script for Qwen model. (#3758)

Include Qwen2VLDecoderLayer in the smooth_qwen2_model function.



fix: PP4 fixes and cleanup (#3688)




remove benchmark test list (#3643)



skip disagg deepseek test if sm!=90 (#3720)



test: skip failed cases on B200 (#3710)

* add skip condition to tests



* fix error



---------



test: [nvbug: 5234494] skip_pre_ada for fp8 cases (#3718)

* skip_pre_ada for fp8 cases



* update



* update after rebase



---------



add know issue to deepseek doc. (#3800)



Fix ModelOpt Mixtral AWQ OOM (#3714) (#3761)




Waive L0 tests (#3826)



fix: Reduce memory usage in fused moe op associated with AutoTuning and fix moe fallback issue. (#3793)

* Reduce memory usage in fused moe op associated with AutoTuning.
* Replace pre-defined bucket size strategy with a generating function based on the tune_max_num_tokens.
* Add free_memory logic of workspace in min_latency_mode fused moe path.



* Fix fused_moe fallback issue. (#3652)

min_latency_mode is only set to False during warmup phase. Thus when it becomes true during inference, all tactics fall back to the default one and thus cause perf regression.



---------



[doc] Better document for Draft-Target-Model (DTM) speculative decoding (#3797)




Fix pre-commit



Fix again



Address some review comments for the MI

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-29 16:57:22 +08:00
Jinyang Yuan
dafc28fb85
fix: Fix FMHA-based MLA in the generation phase and add MLA unit test (#3863) 2025-04-29 09:09:43 +08:00
Xianjie Qiao
3617e948fd
Add docs about DeepSeek-R1 long context support. (#3910) 
* Add docs about DeepSeek-R1 long context support

Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>

* update docs

Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>

* reformat

Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>

---------

Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
 2025-04-28 18:33:05 +08:00
Zhenhuan Chen
ad15e45f07
[TRTLLM-4638 ][feat] add best of n support with reward model in scaffolding (#3807) 
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
 2025-04-28 17:15:33 +08:00
Tao Li @ NVIDIA
2fe35924e3
Fix the link of doc (#3903) 
Signed-off-by: taoli <litaotju@users.noreply.github.com>
Co-authored-by: taoli <litaotju@users.noreply.github.com>
 2025-04-28 14:41:40 +08:00
milesial
362a8272f8
feat: llama4 input processor (#3383) 
Signed-off-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Signed-off-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
Co-authored-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-04-25 16:47:14 -07:00
Mike Iovine
68e774ff9e
[chore] Add Llama 4 Maverick to quickstart README (#3848) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-04-26 01:04:24 +08:00
rakib-hasan
ccd1eb67ec
Adding local paths to the datasets to make them loadable in offline mode (#3750) 
* adding local paths to the datasets to make them loadable in offline mode

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* bert datasets should work on both offline and online mode

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

---------

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
 2025-04-25 03:51:00 +08:00
Luis Vega
f95dbbb6cb
added nemotron-h to supported models (#3663) 
Signed-off-by: Luis Vega <lvega@nvidia.com>
 2025-04-24 10:41:32 -07:00
WeiHaocheng
3fc2a16920
feat(part 2): Enhance the integrated robustness of scaffolding with __init__.py #3305 (#3731) 
Signed-off-by: fredw (generated by with_the_same_user script) <20514172+WeiHaocheng@users.noreply.github.com>
 2025-04-24 18:47:03 +08:00
Zhanrui Sun
ae34d60108
chore: bump version to 0.20.0rc1 (#3834) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-24 17:43:37 +08:00
qixiang-99
3f67a4c9d8
fix: Set default prompts and media for multimodal quickstart example (#3792) 
Signed-off-by: qixiang-99 <203170375+qixiang-99@users.noreply.github.com>
 2025-04-23 22:02:28 -07:00
Mike Iovine
bc5fe7800d
[chore] Fix KV cache block reuse flag name in quickstart_advanced (#3781) 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
 2025-04-24 06:02:47 +08:00
QI JUN
d0d19e81ca
chore: fix some invalid paths of contrib models (#3818) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-24 05:36:16 +08:00
Kaiyu Xie
dfbcb543ce
doc: fix path after examples migration (#3814) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-04-24 02:36:45 +08:00
Daniel Cámpora
1299f27c74
fix: Fix C++ decoder synchronization in PyTorch (#3106) 
* Use updateDecoderBuffers in python decoder.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix synchronize in trtllm decoder.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Enable by default.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Use guided_decoder to setup seqslots and free them.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Use always decode_async and update_requests.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update decoder buffers.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix speculative decoding tests.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Send new_tensors_host instead of assuming dict.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Make default False in enable_trtllm_decoder.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Partially fix mtp, partially fix py_executor.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update request states before sending disagg ctx cache.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix disagg test for torch decoder.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Make isend_tensor_list and recv_tensor_list for sending the tensors_host.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix rebase.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Add disagg serving case to guided decoder.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Get overlap scheduling to work.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update cutlass to main.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update after rebasing.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update to use decode async and update requests.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Properly pass information to update_requests

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Make disaggregated serving a step closer to working.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix rebase.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix rebase and format.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Copy new device tokens more pythonic.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Restore MTP add dummy reqs.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Add ordereddict import to py_executor.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Added seq slot manager. Add test.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Use transmission for single tensor except when list of tensors is received.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Add TRTLLMDecoder allocation to estimate max kv cache tokens.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Add stream synchronization

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Make memory calculation of decoder adapt to the chosen decoder. Recognize decoder option passed in executorconfig. Make overlap scheduler test run on TinyLlama.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Format

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Add decoder creation to estimate max kv.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update submodule UCXX inline with main.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

---------

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-04-23 23:55:27 +08:00
shaharmor98
49262a62a5
add passing E2E LoRA flow (#3788) 
add passing E2E LoRA flow (#3788)

Signed-off-by: Shahar Mor <smor@nvidia.com>
 2025-04-23 18:38:06 +03:00
Enwei Zhu
a51b3cf7a6
[TRTLLM-4763][test] Accuracy test improvement (Part 3.6): Deprecate mmlu_llmapi.py (#3802) 
* cleanup mmlu_llmapi.py

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* polish

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-04-23 23:05:13 +08:00
Zongfei Jing
1e5af736ea
Add smart router for moe (#3641) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-04-23 12:21:59 +08:00
rakib-hasan
b16a127026
fixing the metric fmeasure access (#3774) 
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
 2025-04-23 05:10:04 +08:00
Lucas Liebenwein
06b914e0f9
feat: [AutoDeploy] generalizing cudagraph to multiple dynamic inputs (#3589) 
* generalizing cudagraph to multiple dynamic inputs

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

* fix for failing test

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

---------

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-04-23 03:38:51 +08:00
rakib-hasan
74c13ea84f
datasets API change : datasets.load_metric => evaluate.load (#3741) 
Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
 2025-04-22 08:23:48 +08:00
Enwei Zhu
3fa19ffa4e
test [TRTLLM-4477,TRTLLM-4481]: Accuracy test improvement (Part 3.5): Support GSM8K and GPQA (#3483) 
* add gsm8k

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix gsm8k

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* add gpqa

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* conditional import lm_eval

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* gpqa in lm_eval

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* system prompt

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* shuffle

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* update AA prompt and regex

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* revert AA prompt and regex

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* integration to tests

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* add DS-R1

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix and clean

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* update tests

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* update

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* clean up

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* free_gpu_memory_fraction=0.8

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

* fix

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-04-22 07:38:16 +08:00
katec846
eeb605abd6
feat: Offloading Multimodal embedding table to CPU in Chunked Prefill Mode (#3380) 
* Feat: Offload ptable to cpu if enable_chunk_context

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Feat: offload ptable to cpu for chunk context mode

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Fix and add comment

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Update Readme for multimodal and add a new param mm_embedding_offloading

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* fix: Correct prompt table offloading condition in PromptTuningBuffers

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Clean up the code

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Add commits to explain copy from cpu <-> gpu using pinned memory

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Fix namings based on comments

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Fix format based on precommit

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

* Modify --mm_embedding_offloading flag

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>

---------

Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-04-21 14:31:01 +08:00
hlu1
31624b079a
feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 
* Add TRT-LLM Gen MOE to Deepseek

fix fused moe rebase bug.

Fix atol in test_fp4_gemm_quantize.py

fix fused moe rebase bug.

Fix FusedMoe.

Disable 2nd routing kernel preexit

Bump routing reduction to fp32

Disable PDL for fc1

[DEBUG] Lift token limit to 16k

[Bugfix] Token limit to 16k + fp32 routing + tanh

Make fp8 tileN 8

Fix FP8 MoE + Remove redundent temp output for FP4

[FP8-only] Avoid wasting CTAs for activation kernel

fix: unblock FP8 weightloading with trtllm-gen

Remove max_token limit for trtllm-gen path

perf: avoid type-conversion and fill_ from aten

Minor fix

Signed-off-by: Hao Lu <haolu@nvidia.com>

* Fix rebase issues

Signed-off-by: Hao Lu <haolu@nvidia.com>

* Fix compile issue

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* CI clean

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

---------

Signed-off-by: Hao Lu <haolu@nvidia.com>
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
Co-authored-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-04-21 10:01:33 +08:00
Naveassaf
f7c2eb4fa2
Update Nemotron Super and Ultra in Supported Models and add an example (#3632) 
* Update Nemotron Super and Ultra in Supported Models and add an example

Signed-off-by: Nave Assaf <nassaf@nvidia.com>

* Update README link to match new examples structure

Signed-off-by: Nave Assaf <nassaf@nvidia.com>

---------

Signed-off-by: Nave Assaf <nassaf@nvidia.com>
 2025-04-20 21:14:33 +08:00
QI JUN
d51ae53940
move the reset models into examples/models/core directory (#3555) 
* move rest models to examples/models/core directory

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* update multimodal readme

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix example path

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix cpp test

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix tensorrt test

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

---------

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-19 20:48:59 -07:00
brb-nv
c35d2a7532
test: Get Eagle tests working (#3593) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-20 00:50:57 +08:00
Yechan Kim
5460d18b10
feat: trtllm-serve multimodal support (#3590) 
* feat: trtllm-serve multimodal support

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* remove disable argument

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* remove disable

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* add and separate tests and move the doc

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* remove block_resue arg from serve.py

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

---------

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-04-19 05:01:28 +08:00
mayani-nv
ce8329646f
Update run.py for draft_target_model (#3615) 
This change makes the draft target model works without mismatch in the vocab size

Signed-off-by: mayani-nv <67936769+mayani-nv@users.noreply.github.com>
Co-authored-by: rakib-hasan <rhasan@nvidia.com>
 2025-04-19 01:01:50 +08:00
Zheng Duan
bce7ea8c38
test: add kv cache event tests for disagg workers (#3602) 2025-04-18 18:30:19 +08:00
Dom Brown
dbd9a83b0d
feat: Integrate GPUDirect Storage (GDS) into Executor API (#3582) 
* feat: Integrate GPUDirect Storage (GDS) into Executor API

Squash of several dev commits

Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
 2025-04-18 15:59:21 +08:00
Zheyu Fu
90a28b917f
feat: Add Dynasor-CoT in scaffolding examples. (#3501) 
Signed-off-by: Zheyu Fu <zheyufu2@gmail.com>
Co-authored-by: Junda Chen <32371474+GindaChen@users.noreply.github.com>
Co-authored-by: Yichao Fu <57950249+fuyichao2000@users.noreply.github.com>
Co-authored-by: Andy Dai <zhongdongmin@nvidia.com>
 2025-04-18 07:48:01 +00:00
Yuan Tong
0b0e6d8a0a
refactor: Clean up CMakeLists.txt (#3479) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-04-18 14:39:29 +08:00
rakib-hasan
ff3b741045
feat: adding multimodal (only image for now) support in trtllm-bench (#3490) 
* feat: adding multimodal (only image for now) support in trtllm-bench

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* fix: add  in load_dataset() calls to maintain the v2.19.2 behavior

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* re-adding prompt_token_ids and using that for prompt_len

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* updating the datasets version in examples as well

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* api changes are not needed

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* moving datasets requirement and removing a missed api change

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* addressing review comments

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

* refactoring the quickstart example

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>

---------

Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
 2025-04-18 07:06:16 +08:00
Tao Li @ NVIDIA
e4476bf521
update fp8 doc (#3647) (#3650) 
Signed-off-by: taoli <litaotju@users.noreply.github.com>
Co-authored-by: taoli <litaotju@users.noreply.github.com>
 2025-04-17 13:37:08 +08:00
Zhanrui Sun
9d88ee3e45
chore: bump version to 0.20.0rc0 (#3561) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-16 11:41:21 +08:00
narutolhy
ccd73c71a5
feat: Add stream generation task scaffolding examples (#3527) 
* stream generation task/controller

Signed-off-by: narutolhy <582909902@qq.com>

* edit README

Signed-off-by: narutolhy <582909902@qq.com>

* rename README

Signed-off-by: narutolhy <582909902@qq.com>

---------

Signed-off-by: narutolhy <582909902@qq.com>
 2025-04-16 11:33:55 +08:00
Kaiyu Xie
f5f68ded26
Minor fixes for documents (#3577) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-04-16 07:47:18 +08:00
Pengyun Lin
1899e71364
doc: add genai-perf benchmark & slurm multi-node for trtllm-serve doc (#3407) 
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com>
 2025-04-16 00:11:58 +08:00
nv-guomingz
39bdb1fe1c
docs:update llm api examples and customizations sections' links. (#3566) 
Signed-off-by: nv-guomingz <37257613+nv-guomingz@users.noreply.github.com>
 2025-04-15 13:55:22 +08:00
Bo Li
5eae397b3b
doc: Update instructions to enable FP8 MLA for Deepseek. (#3488) 
* doc: Update doc to enable FP8 MLA for Deepseek.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

* Update.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

* Update.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

* Update the status on Hopper and Blackwell.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

* Update.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

* Update table of contents.

Signed-off-by: Bo Li <bobboli0202@gmail.com>

---------

Signed-off-by: Bo Li <bobboli0202@gmail.com>
Co-authored-by: bhsueh_NV <11360707+byshiue@users.noreply.github.com>
 2025-04-15 13:12:33 +08:00
Zhanrui Sun
714ff3eedd
chore: bump version to 0.19.0rc0 (#3535) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-14 18:11:20 +08:00
Zhanrui Sun
ee4ce0379d
chore: bump version to 0.19.0rc0 (#3514) 
* chore: bump version to 0.19.0.rc0

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>

* Update README

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-14 17:32:30 +08:00
Kaiyu Xie
f99be2726f
doc: Add example section for multi-node DeepSeek R1 benchmark on GB200 (#3519) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-04-14 16:45:55 +08:00
brb-nv
44090a5388
Add support for Phi-4-MM (#3296) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-14 14:24:10 +08:00
Yan Chunwei
b37c5c0a4d
make LLM-API slurm examples executable (#3402) 
Signed-off-by: chunweiy <328693+Superjomn@users.noreply.github.com>
 2025-04-13 21:42:45 +08:00
QI JUN
d167cbd5bb
refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370) 
* remove tensorrt_llm._torch.distributed.ParallelConfig

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* clean

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix embedding test

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix comments

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* polish

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* fix ci

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

* rebase

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

---------

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>
 2025-04-11 15:34:20 -07:00
Shunkangz
ea050084ad
feat: Add support of chat completion in PD (#2985) 
* Add support of chat completion in PD

Add support of include_usage in PD


Reformat


* Remove redundant code

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

* Refactor code

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

* Add chat completion test

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

* Refactor code

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>

---------

Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
 2025-04-11 17:53:28 +08:00
amitz-nv
a6a2ae6cc1
chore: Rename nvsmall to nemotron nas (#3447) 
* Rename nvsmall to nemotron NAS

* Revert nvsmall to nemotron_nas rename in paths in tests that access llm_models_root/nvsmall/tests

* Add NemotronNAS to pytorch supported models table

Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>
 2025-04-10 23:16:52 +08:00
wm2012011492
af05749e90
feat: add qwen2 moe to torch flow; fix wrong imported KvCacheConfig in gpqa… (#3369) 
* add qwen2 moe to torch flow; fix wrong imported KvCacheConfig in gpqa_llmapi.py

Signed-off-by: mengw <12670782+wm2012011492@users.noreply.github.com>

* fix coding style

Signed-off-by: mengw <12670782+wm2012011492@users.noreply.github.com>

* add unittest

Signed-off-by: mengw <12670782+wm2012011492@users.noreply.github.com>

---------

Signed-off-by: mengw <12670782+wm2012011492@users.noreply.github.com>
Co-authored-by: mengw <12670782+wm2012011492@users.noreply.github.com>
 2025-04-10 22:45:57 +08:00
Kefeng-Duan
67949f7c39
Update README and add benchmarking blog for DeepSeek-R1 (#3232) 
- Added a new entry in the README for the published benchmarking best practices for DeepSeek-R1.
- Introduced a new blog post detailing performance benchmarking configurations and procedures for DeepSeek-R1 in TensorRT-LLM, including installation, dataset preparation, and benchmarking steps for both B200 and H200 GPUs.

Signed-off-by: taoli <litaotju@users.noreply.github.com>
Co-authored-by: taoli <litaotju@users.noreply.github.com>
 2025-04-10 17:00:49 +08:00
brb-nv
c59abae436
feat: Add Gemma3 text-only model support (#3247) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-10 12:34:58 +08:00
Yechan Kim
943218b54a
feat: Add Qwen2.5-VL and refactor Qwen2-VL (#3156) 
* feat: Add Qwen2.5-VL and refactor Qwen2-VL

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix yapf and codespell

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* add test

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix test_e2e

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* generalize get_rope_index

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix qwen2.5-vl on REAME

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix test

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

* fix image test

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>

---------

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
 2025-04-10 04:09:03 +08:00
WeiHaocheng
6eee15900e
feat: Enhance the integrated robustness of scaffolding with __init__.py #3305 (#3312) 
Signed-off-by: fredw (generated by with_the_same_user script) <20514172+WeiHaocheng@users.noreply.github.com>
 2025-04-09 21:13:47 +08:00