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
283 Commits 25 Branches 59 Tags 2.1 GiB
385a01055c
Commit Graph

283 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kaiyu Xie
385a01055c
doc: Add serving section for DS V3 document (#3262) 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
 2025-04-03 21:57:48 +08:00
Zhanrui Sun
bd75ec02f2
Fix bot check error when triggered by pull request (#3268) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-03 21:47:05 +08:00
Fanrong Li
11624a8e96
fix deepseek-v3 mtp doc. (#3272) 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Co-authored-by: juney-nvidia <143764042+juney-nvidia@users.noreply.github.com>
 2025-04-03 21:12:17 +08:00
Yechan Kim
c7533d271f
doc: add supported-models on PyTorch example (#3179) 
* doc: add supported-models on PyTorch example

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

* remove vision support from Llama3.2

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: juney-nvidia <143764042+juney-nvidia@users.noreply.github.com>
 2025-04-03 21:09:25 +08:00
Yukun He
d138795485
Fix minor issues in test_autotuner.py and loose the cache check for test gemms. (#3261) 
This test can cause nondeterministic failures on CI with unexpected kernel profiling results. Given longer delay time or cache clear will not solve the issue. Thus, loose the test checks to avoid these false alarms.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
 2025-04-03 18:24:08 +08:00
Zhanrui Sun
67e9f99d46
infra: [TRTLLM-4308] Add Bot help (#3192) 
* Add bot command help and check bot command

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

* Fix permission error

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

* Fix add comment

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

* Fix

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

* Fix review

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

* Update bot-command.yml

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

* Apply suggestions from code review

Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>

* Update .github/workflows/bot-command.yml

Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>

* Fix pre-commit

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

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
 2025-04-03 17:48:25 +08:00
Zhanrui Sun
587a36db96
infra: [TRTLLM-4370] Fix the build error when build GH200 image (#3229) 
* infra: Fix the build error when build GH200 image

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

* remove and update checkoutSource function

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

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-03 17:33:50 +08:00
xinhe-nv
2005e5aaaf
remove tests from qa test lists (#3256) 
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
 2025-04-03 16:06:39 +08:00
xiweny
174a5af779
doc: refine integration test guide (#3215) 
* doc: refine integration test guide

Signed-off-by: Xiwen Yu <xiweny@nvidia.com>
 2025-04-03 15:36:13 +08:00
Fanrong Li
1fe64b90be
fix: fix the acceptance rate of pytorch workflow in trtllm-bench (#3240) 
* fix acceptance rate of pytorch workflow.
* revert the RequestOutput API change.

---------

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
 2025-04-03 15:12:24 +08:00
Frank
2d80db4c36
chore: Remove build config from Pytorch kwargs. (#3210) 
Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
 2025-04-03 15:00:29 +08:00
Zhanrui Sun
7f03125098
test: [TRTLLM-3994] Support only run pytorch tests (#3013) 
* [TRTLLM-3994] Support only run pytorch tests

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

* Move perf test to TensorRT backend

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

* Fix review

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

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-03 13:46:09 +08:00
Zongfei Jing
dcc0ebd273
Fix warning (#3254) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-04-03 13:30:23 +08:00
pcastonguay
b5b83009ff
chore: Reenabling get_stats_async test which seems to have been fixed by recent commit (#3246) 
Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com>
 2025-04-02 20:57:31 -07:00
Jinyang Yuan
2fdfa39ea8
fix: Fix an error related to dummy request when MTP is used (#3146) 2025-04-03 11:08:12 +08:00
QI JUN
664f428476
set test timeout threshold to 5400 second (#3249) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-03 10:14:00 +08:00
Ming Wei
ca6615d800
Remove gen_cuda_headers_for_xqa.py (#3222) 
No longer needed.
 2025-04-03 07:13:22 +08:00
Chuang Zhu
f5bf74bc7f
enable some disagg test (#3203) 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
 2025-04-03 06:10:48 +08:00
Anurag Mukkara
d998339855
Raise error for PP + MTP (#3244) 
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
 2025-04-03 04:45:31 +08:00
Lucas Liebenwein
5fc2f63fec
infra: Devcontainer productivity improvements (#3075) 
* devcontainer improvements

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

* docker compose path

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

* updated some more devcontainer settings

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

* clean devcontainer name

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

---------

Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
 2025-04-03 02:23:38 +08:00
QI JUN
abcb0486dc
fix deepseek failure with pipeline parallelism (#3225) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-02 22:56:39 +08:00
Robin Kobus
b5bc0a9fcd
chore: Add output of first token to additional generation outputs (#3205) 
- Updated the first dimension of additional output tensors to match mMaxNewTokens.
- Copy output of last context token to generation outputs.
- Adjusted the expected output size calculations in unit tests to reflect the correct maximum output length.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-04-02 20:14:16 +08:00
Zheng Duan
c9e94ec807
fix: remove test relies on timing (#3228) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-04-02 18:38:37 +08:00
WeiHaocheng
228e453780
doc: add doc ahout developent on cloud or runpod (#3194) 
Signed-off-by: fredw <20514172+WeiHaocheng@users.noreply.github.com>
 2025-04-02 18:10:56 +08:00
Enwei Zhu
3cf7066350
test: Accuracy test improvement (Part 3.2): Move Qwen tests (NvBug 5135332) (#3219) 
* remove test_llm_models_multi_gpu.py

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

* fix

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

* qwen 2.5

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

* fix

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

* upgrade

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

---------

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-04-02 17:29:57 +08:00
Enwei Zhu
d3948cd9b2
fix: GPT-Next convert failure (#3220) 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
 2025-04-02 17:14:39 +08:00
WeiHaocheng
e64c565750
doc: add a directory for scaffolding contributors (#3224) 
Signed-off-by: fredw <20514172+WeiHaocheng@users.noreply.github.com>
 2025-04-02 16:08:00 +08:00
Zheng Duan
5a72945eec
fix: conditional disagg test name (#3161) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-04-02 15:34:30 +08:00
William Tambellini
dbc0496f37
fix: upgrade cmake minimum from 3.18 to 3.27 (#3208) 
Required to correctly support recent archs like 90a, ...
Fix issue #3173

Signed-off-by: William Tambellini <wtambellini@sdl.com>
Co-authored-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
 2025-04-02 15:14:36 +08:00
Julien Debache
76a6a62073
fix: segfault in cudaDriverWrapper (#3017) 
* fix segmentation fault in cudaDriverWrapper

Signed-off-by: jdebache <jdebache@nvidia.com>

* replace cuGetErrorMessage with cuGetErrorString and added tests

Signed-off-by: jdebache <jdebache@nvidia.com>

---------

Signed-off-by: jdebache <jdebache@nvidia.com>
 2025-04-02 08:55:19 +02:00
Zongfei Jing
8d48b96545
reduce test cases for deepseek (#3211) 
Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-04-02 13:57:55 +08:00
wili
34e63d07e6
feat: Variable-Beam-Width-Search (VBWS) Part2 (#3133) 
* feat: Variable-Beam-Width-Search Part2

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search Part2

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search Part2, fix CPP tests

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search Part3, simplify CPP tests

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search Part4, move beam_width_array param

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search, fix CI error

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search part2

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search part2

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search part2, fix pre-commit

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

* feat: Variable-Beam-Width-Search part2, fix review

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>

---------

Signed-off-by: wili-65535 <wili-65535@user.noreply.github.com>
Co-authored-by: wili-65535 <wili-65535@user.noreply.github.com>
 2025-04-02 12:31:28 +08:00
Gabriel Wu
05b50b297f
[feat] open source fp8_blockscale_gemm (#3071) 
Signed-off-by: Zihua Wu <zihuaw@nvidia.com>
 2025-04-02 12:12:52 +08:00
Yiqing Yan
c19b7f7c2a
waive L0 test (#3217) 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
 2025-04-02 11:16:22 +08:00
QI JUN
bb10cdcfb8
chore: refine fetch new requests method (#3213) 
* refine broadcast new requests method

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

* refine fetch new requests method

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

---------

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-02 10:46:00 +08:00
Zhanrui Sun
c5199c0b3d
infra: Support get file change for github PR (#3098) 
* Support get file change for github PR

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

* Fix reviews

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

* Check if only pytorch related file changed

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

* Fix

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

* Fix global var

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

* Use globalVars for global values

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

* Fix

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

* Fix review

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

---------

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-02 10:35:33 +08:00
Zheng Duan
35b828ca2d
fix streaming in dist-serving (#3087) 
Signed-off-by: Zheng Duan <200704041+zhengd-nv@users.noreply.github.com>
 2025-04-02 10:08:07 +08:00
Chuang Zhu
bc5811da65
chore: Ucx ip port remove mpi depend (#3101) 
* initial ucx support

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* fixes to support dynloading and ucx connection establishment - not stable yet

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* update

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* more connection bringup fixes - faillig on connection vector build

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* executor test pass

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* update

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* passed full benchmark

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* changing to TLLM_THROW and removing cout

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* stoping progress thread at ucxComm destructor

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* fixing build with ENABLE_UCX=0 to not build ucx traget at all and removing includes for ucxConnection for cache transceiver, also delete commented cold code

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* fix copyrights

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* adding ucx flavor to cache transceiver test and insertto the CI pipeline

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* allowing sending non ib interfaces IPs

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* setting UCX port reuse for the tests in pipeline

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* code review fixes

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* querying ep after GID message is sent to avoid UCX Errors

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* fixing more CR issues

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* querying ep to not fail is ep_not_connected yet

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>

* remove mpi dependency and debug

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* debug to info

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* mpirun n 2

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* remove mpi comm split when disaggOrchestrator mode

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* waive disagg_mtp test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* use future instead of thread

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* use future_promise instead of cv wait

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* connectionId type

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* improve test

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* imporve test 2

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

* gtest_skip

Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>

---------

Signed-off-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Co-authored-by: roeya <165803633+RoeyAzran1992@users.noreply.github.com>
 2025-04-02 09:42:29 +08:00
Zongfei Jing
c7548ad72c
perf: Add optimizations for deepseek in min latency mode (#3093) 
* Add optimizations for deepseek min latency

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

* Fix compile error

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

* Update internal cutlass kernel libs

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

* Format code

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

* Resolve conflicts

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

---------

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
 2025-04-02 09:05:24 +08:00
brb-nv
1fe3e30356
Add support for Phi-4-mini (#2990) 
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
 2025-04-02 08:34:39 +08:00
Zhanrui Sun
42963baacd
chore: bump version to 0.19.0.dev2025040800 (#3171) 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
 2025-04-02 08:21:55 +08:00
QI JUN
8fe2e5865e
refine broadcast new requests method (#3198) 
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
 2025-04-02 08:05:20 +08:00
Fridah-nv
a5f32f46fd
fix: [AutoDeploy] Update README.md (#3072) 
* update support matrix and add toggle list

Signed-off-by: fridah <201670829+Fridah-nv@users.noreply.github.com>

* Update README.md

Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>

* Update README.md

Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>

---------

Signed-off-by: fridah <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
 2025-04-01 16:16:36 -07:00
Chang Liu
1d3a5d38af
fix: Update FP8 sf layout for Blackwell and relax blockwise GEMM assertions (#3144) 
* Update fp8 sf layout for blackwell and enable fp8 gemm e2e

* Add test case when m needs to be padded

* Better comment

Signed-off-by: Chang Liu <liuc@nvidia.com>

* Add TODO for fp8 quant kernel

Signed-off-by: Chang Liu <liuc@nvidia.com>

* Enable DCO check

Signed-off-by: Chang Liu <liuc@nvidia.com>

* Fix lint

---------

Signed-off-by: Chang Liu <liuc@nvidia.com>
 2025-04-01 13:08:29 -07:00
Robin Kobus
d880f4a7c6
chore: Cursor ignore cubin in headers (#3202) 
Add `*cubin.h` to ignore-file.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-04-01 23:42:19 +08:00
Enwei Zhu
b2f69db507
test: Accuracy test improvement (Part 3.1): Extend accuracy test suite with LLM API and initial implementation of trtllm-eval (#3167) 
* add eval_llmapi

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

tmp commit

port to CLI tool

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

move

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

setup llmapi

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

fix spec_dec_algo

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

_update_from_hf_quant_config

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

fix

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

migrate test_pytorch.py

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

fix fp8 block scales

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

fix fp8 rowwise

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

adj alpha

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

move test_pytorch.py cases

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

move

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

rename test_accuracy.py to test_cli.py

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

clean

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

* fix cnn_dailymail

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

* renaming to cli flow

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

* rename MMLU

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

* rename

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

* add error

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>
 2025-04-01 22:20:29 +08:00
amirkl94
bf02b9144f
feature: Add LoRA support for gemma (#3068) 
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
 2025-04-01 19:15:55 +08:00
Robin Kobus
d7386d14a8
refactor: Simplify disableLookahead and improve numDecodingEngineTokens handling (#3103) 
* refactor: Simplifiy disableLookahead method

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* Update DecoderBuffers comments

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Move numDecodingEngineTokens to DecoderState

This commit introduces new methods in the DecoderState class to manage the number of tokens for each request in a batch. The following changes were made:
- Added `getNumDecodingEngineTokens()` to retrieve the number of tokens for all requests.
- Added `getNumDecodingEngineTokens(SizeType32 batchIdx)` to get the token count for a specific request.
- Added `setNumDecodingEngineTokens(SizeType32 batchIdx, SizeType32 numTokens)` to set the token count for a specific request.
- Updated the setup method to initialize the token count vector based on the maximum batch size.
- Refactored the `CreateNewDecoderRequests` class to utilize the new token management methods, improving clarity and maintainability.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* refactor: Improve shape variables in DecoderState

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
 2025-04-01 18:47:31 +08:00
WeiHaocheng
ff35af77ea
feat: refactor scaffolding worker and support openai api worker (#3166) 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
Signed-off-by: fredw <20514172+WeiHaocheng@users.noreply.github.com>
 2025-04-01 18:31:52 +08:00
bhsueh_NV
d34202273b
fix bug of glm-4-9b ci (#3184) bug nvbug_5196515 
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
 2025-04-01 16:58:42 +08:00