Commits · 7da296be04933cfc29031f5bd1ba7cd28f376faa · OpenDAS / vllm_cscc

02 Jul, 2025 5 commits
- [TPU] kv cache update kernel supports dynamic grid (#20235) · 7da296be
  Chengji Yao authored Jul 01, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  7da296be
- [Refactor] Remove duplicate `find_free_port` (#20333) · 7058d7dd
  Wentao Ye authored Jul 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  7058d7dd
- [UT][intel GPU] use current_platform instead of device hardcode in v1 tests (#20169) · a0389e05
  Liangliang Ma authored Jul 02, 2025
```
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
```
  a0389e05
- Enable group size 64 for Machete (#20290) · 3abfe221
  czhu-cohere authored Jul 01, 2025
```
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
```
  3abfe221
- [Refactor] Refactor import utils (#20269) · e81fbefe
  Wentao Ye authored Jul 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  e81fbefe
01 Jul, 2025 12 commits
- [Optimization] Cache sampled token ids in model runner (#20291) · 7f280d69
  Woosuk Kwon authored Jul 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  7f280d69
- [Model]Add Tencent HunYuanMoEV1 Model Support (#20114) · ecad851c
  aiyiwang2025 authored Jul 01, 2025
```
Signed-off-by: aiyiwang <aiyiwang@tencent.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: quinnrong <quinnrong@tencent.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  ecad851c
- Add GLM4.1V model (Draft) (#19331) · ed70f3c6
  Yuxuan Zhang authored Jul 01, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  ed70f3c6
- [Quant] [Bugfix] Fix quantization config matching with `hf_to_vllm_mapper` (#20046) · 9025a9a7
  Kyle Sayers authored Jul 01, 2025
  
  9025a9a7
- [Perf] Validate @config in pre-commit instead of dynamically (#20200) · c05596f1
  Lionel Villard authored Jul 01, 2025
```
Signed-off-by: Lionel Villard <villard@us.ibm.com>
```
  c05596f1
- [BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067) · 96453cfa
  TY-AMD authored Jul 01, 2025
```
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
```
  96453cfa
- [Bugfix] Fix deepep tests (#20288) · 08d81f10
  Varun Sundar Rabindranath authored Jul 01, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  08d81f10
- [CPU] Update custom ops for the CPU backend (#20255) · 6cc1e7d9
  Li, Jiang authored Jul 01, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  6cc1e7d9
- Enable ZP Support for Machete (#20268) · 9909726d
  czhu-cohere authored Jul 01, 2025
```
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
```
  9909726d
- [Feature] A calibration-free RTN-based quantization for accurate and... · 27949354
  Alex Kogan authored Jul 01, 2025
```
[Feature] A calibration-free RTN-based quantization for accurate and accelerated INT4/INT8 inference (#18768)
Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  27949354
- [Bugfix] Fix include prompt in stream response when echo=true (#15233) · e28533a1
  fyuan1316 authored Jul 01, 2025
```
Signed-off-by: Yuan Fang <yuanfang@alauda.io>
```
  e28533a1
- [CLI] Improve CLI arg parsing for `-O`/`--compilation-config` (#20156) · 6d42ce83
  Luka Govedič authored Jun 30, 2025
```
Signed-off-by: luka <luka@neuralmagic.com>
```
  6d42ce83
30 Jun, 2025 4 commits
- [Core] [Bugfix] [Multimodal] Fix multimodal profiling and generation for SFT/PTQed models (#20058) · d8cf819a
  Kyle Sayers authored Jun 30, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  d8cf819a
- [Unit Test] Add unit test for deep gemm (#20090) · 551ef163
  Wentao Ye authored Jun 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  551ef163
- [Optimization] Use Shared `CachedRequestData` Instance Across All Requests (#20232) · 2863befc
  Woosuk Kwon authored Jun 30, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2863befc
- [Model] support dots1 (#18254) · 65b1cbb1
  redmoe-moutain authored Jun 30, 2025
```
Signed-off-by: redmoe-moutain <agiredmoe@gmail.com>
```
  65b1cbb1
29 Jun, 2025 2 commits
- [Quantization] Add compressed-tensors NVFP4 MoE Support (#19990) · 6f2f53a8
  Dipika Sikka authored Jun 30, 2025
```
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
```
  6f2f53a8
- [CI Fix] Try fixing eagle e2e test OOM by reducing block allocation (#20213) · 7b1895e6
  Michael Goin authored Jun 29, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  7b1895e6
28 Jun, 2025 5 commits
- [Refactor] Create a function util and cache the results for `has_deepgemm`,... · 4d366936
  Wentao Ye authored Jun 28, 2025
```
[Refactor] Create a function util and cache the results for `has_deepgemm`, `has_deepep`, `has_pplx` (#20187)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  4d366936
- [Bugfix] Correct behavior of GraniteMoeHybrid for TensorParallel execution (#20137) · daec9dea
  Stan Wozniak authored Jun 28, 2025
```
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
```
  daec9dea
- [CI/Build] Add new CI job to validate Hybrid Models for every PR (#20147) · 8615d977
  Thomas Parnell authored Jun 28, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  8615d977
- [Misc] Add type assertion of request_id for LLMEngine.add_request (#19700) · e53be6f0
  Chales Xu authored Jun 28, 2025
```
Signed-off-by: n2ptr <xuzhanchaomail@163.com>
```
  e53be6f0
- [CI Fix] Pin tests/models/registry.py MiniMaxText01ForCausalLM to revision due... · c329ceca
  Michael Goin authored Jun 28, 2025
```
[CI Fix] Pin tests/models/registry.py MiniMaxText01ForCausalLM to revision due to model changes (#20199)
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c329ceca
27 Jun, 2025 8 commits

[Fix][torch.compile] Enable custom ops by default when Inductor off (#20102) · aafabaa0
Luka Govedič authored Jun 27, 2025
```
Signed-off-by: luka <luka@neuralmagic.com>
```
aafabaa0

Gemma3n (Text-only) (#20134) · d1c956dc

Robert Shaw authored Jun 27, 2025


Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>

d1c956dc

[Perf][Frontend] eliminate api_key and x_request_id headers middleware overhead (#19946) · 6e244ae0
Yazan Sharaya authored Jun 27, 2025
```
Signed-off-by: Yazan-Sharaya <yazan.sharaya.yes@gmail.com>
```
6e244ae0
[Model][1/N] Automatic conversion of CrossEncoding model (#20012) · cd4cfee6
wang.yuqi authored Jun 27, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
cd4cfee6
[Fix] Fix gemma CI test failing on main (#20124) · e1109306
Thomas Parnell authored Jun 27, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
e1109306

[CI] Sync test dependency with test.in for torch nightly (#19632) · 8b64c895

Yang Wang authored Jun 26, 2025


Signed-off-by: Yang Wang <elainewy@meta.com>
Signed-off-by: Yida Wu <yidawu@alumni.cmu.edu>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Concurrensee <yida.wu@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

8b64c895

[Feature] add quick all reduce (#19744) · 0740e29b

li haoyang authored Jun 27, 2025


Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>

0740e29b

[CI Failure] Fix OOM with test_oot_registration_embedding (#20144) · 71799fd0
Michael Goin authored Jun 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
71799fd0

26 Jun, 2025 4 commits
- [Feature] Expert Parallelism Load Balancer (EPLB) (#18343) · e9fd658a
  Bowen Wang authored Jun 26, 2025
```
Signed-off-by: Bowen Wang <abmfy@icloud.com>
```
  e9fd658a
- [Refactor] Rename commnication utils (#20091) · 56230881
  Wentao Ye authored Jun 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  56230881
- [TPU] add kv cache update kernel (#19928) · 04e1642e
  Chengji Yao authored Jun 26, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  04e1642e
- [Bug Fix] Fix address/port already in use error for deep_ep test (#20094) · c894c5dc
  Wentao Ye authored Jun 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c894c5dc