Commits · a4113b035cd4ee90ec02de0658b75d47f0007ede · OpenDAS / vllm_cscc · GitLab

04 Jul, 2025 2 commits
- [Platform] Add custom default max tokens (#18557) · a4113b03
  Gabriel Marinho authored Jul 03, 2025
```
Signed-off-by: Gabriel Marinho <gmarinho@ibm.com>
```
  a4113b03
- [Misc] Change warn_for_unimplemented_methods to debug (#20455) · 7e1665b0
  Michael Goin authored Jul 04, 2025
  
  7e1665b0
03 Jul, 2025 17 commits
- [Bugfix] Register reducer even if transformers_modules not available (#19510) · 8d1096e7
  Seiji Eicher authored Jul 03, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  8d1096e7
- [Misc] Fix `Unable to detect current VLLM config. Defaulting to NHD kv cache... · 8d775dd3
  Nicolò Lucchesi authored Jul 03, 2025
```
[Misc] Fix `Unable to detect current VLLM config. Defaulting to NHD kv cache layout` warning (#20400)
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  8d775dd3
- [Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864) · 78fe7753
  bnellnm authored Jul 03, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  78fe7753
- [Misc] Remove _maybe_ignore_quant_config from GLM4.1v (#20432) · 2f2fcb31
  Yuxuan Zhang authored Jul 04, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
  2f2fcb31
- [Misc] adjust for ipv6 for mookcacke url parse (#20107) · 1dba2c4e
  Ning Xie authored Jul 04, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  1dba2c4e
- [Misc] Clean up InternVL family config registration (#19992) · 71d6de3a
  Isotr0py authored Jul 04, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  71d6de3a
- [Frontend] fix duplicate output for bench subcmd (#20446) · 619b9f5c
  Reid authored Jul 03, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
```
  619b9f5c
- [Frontend] improve vllm bench <bench_type> --help display (#20430) · 9854dc90
  Reid authored Jul 03, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
```
  9854dc90
- [Model][2/N] Automatic conversion of CrossEncoding model (#19978) · 6f1229f9
  wang.yuqi authored Jul 03, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  6f1229f9
- [Quantization] Bump to use latest bitsandbytes (#20424) · 1819fbda
  Jee Jee Li authored Jul 03, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1819fbda
- [Kernel] refactor cpu worker v0 cache dtype (#20080) · fb14d53c
  Ning Xie authored Jul 03, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  fb14d53c
- [Core] Move multimodal placeholder from chat utils to model definition (#20355) · b024a42e
  Cyrus Leung authored Jul 03, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b024a42e
- [Feature] Support MiniMax-M1 function calls features (#20297) · 363528de
  qscqesze authored Jul 03, 2025
```
Signed-off-by: QscQ <qscqesze@gmail.com>
Signed-off-by: qingjun <qingjun@minimaxi.com>
```
  363528de
- [Bugfix][CI/CD][CPU] Fix CPU CI tests (#20383) · 0ec3779d
  Li, Jiang authored Jul 03, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  0ec3779d
- [Misc] Small: Fix video loader return type annotations. (#20389) · b616f6a5
  Chenheli Hua authored Jul 02, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  b616f6a5
- [Bugfix] Fix import of CutlassExpertsFp8 in compressed_tensors_moe.py (#20381) · 2e25bb12
  bnellnm authored Jul 02, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  2e25bb12
- [BugFix] Fix DP headless mode arg validation (#20398) · 059d4cdb
  Nick Hill authored Jul 03, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  059d4cdb
02 Jul, 2025 20 commits
- [DP] Support external DP Load Balancer mode (#19790) · 657f2f30
  Nick Hill authored Jul 02, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  657f2f30
- [ROCm][FEAT] Enable Full Graph Mode in AITER MLA V1 Attn Backend (Decode Phase only) (#20254) · a1aafc82
  vllmellm authored Jul 03, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  a1aafc82
- [Misc] add handler HF_TOKEN is emptry string (#20369) · 139508a4
  rongfu.leng authored Jul 03, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  139508a4
- [V1] LogitsProcessor programming model (#16728) · 48fb076c
  afeldman-nm authored Jul 02, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  48fb076c
- [Kernels] MoE refactor (#19636) · c1909e7e
  bnellnm authored Jul 02, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
```
  c1909e7e
- [Model] Adds support for SlimMoE models Phi-tiny-MoE-instruct (#20286) · 706ff132
  zichongli5 authored Jul 02, 2025
```
Signed-off-by: Zichong Li <t-lizichong@microsoft.com@Reasoning-H100-VM3.drbuo4tcjzruhloch3eo0b25ef.cx.internal.cloudapp.net>
Co-authored-by: Zichong Li <t-lizichong@microsoft.com@Reasoning-H100-VM3.drbuo4tcjzruhloch3eo0b25ef.cx.internal.cloudapp.net>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  706ff132
- [Bugfix] Fix the max_seq_len limit of 16384 for DeepSeek models (#20322) · ccbfb1d1
  WangHuaqiang authored Jul 02, 2025
```
Signed-off-by: Wang Huaqiang <huaqiang.wang@intel.com>
```
  ccbfb1d1
- [Model] Add Ernie4.5 and Ernie4.5MoE Model Support (#20220) · e303dcf5
  CSWYF3634076 authored Jul 02, 2025
```
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
```
  e303dcf5
- [Bugfix] Keye-VL compatibility with `tok_kwargs` (#20058) (#20353) · ba51aea6
  Cyrus Leung authored Jul 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ba51aea6
- [Model][VLM] Support Keye-VL-8B-Preview (#20126) · 8452946c
  Kwai-Keye authored Jul 02, 2025
```
Signed-off-by: Kwai-Keye <Keye@kuaishou.com>
```
  8452946c
- [Frontend] Support configurable mm placeholder strings & flexible video... · 2e7cbf2d
  Chenheli Hua authored Jul 01, 2025
```
[Frontend] Support configurable mm placeholder strings & flexible video sampling policies via CLI flags. (#20105)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  2e7cbf2d
- [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
- [Bugfix] Fix dynamic rotary embedding (#20343) · 1a03dd49
  Cyrus Leung authored Jul 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  1a03dd49
- [FIX][Intel GPU]fix ipex flash_attn_varlen_func api missing parameter (#20348) · 27b80176
  Kunshang Ji authored Jul 02, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  27b80176
- [Misc][Doc] Add missing comment for LLM (#20285) · 9ec1e306
  Lifans authored Jul 01, 2025
```
Signed-off-by: Lifan Shen <lifans@meta.com>
```
  9ec1e306
- [Refactor] Remove Unused Env `VLLM_ENABLE_MOE_ALIGN_BLOCK_SIZE_TRITON` (#20334) · 9dae7d46
  Wentao Ye authored Jul 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  9dae7d46
- [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 1 commit
- [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