Commits · 98deac3879860b829dd9a30b19bbb2adb9c96e7f · OpenDAS / vllm_cscc · GitLab

13 Aug, 2025 22 commits
- [FEATURE] support custom vllm tuned config path for fused moe triton kernels (#22791) · 98deac38
  Chi Zhang authored Aug 13, 2025
```
Signed-off-by: Chi Zhang <zhangchi.usc1992@bytedance.com>
```
  98deac38
- [Frontend] Add chunked processing to handle long inputs in embedding models (#22280) · 653124bd
  Kdump authored Aug 13, 2025
```
Signed-off-by: x22x22 <wadeking@qq.com>
Signed-off-by: Kdump <rootshellexp@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Maximilien de Bayser <maxdebayser@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  653124bd
- [Platform] Custom ops support for FusedMoe (#22509) · 0b1bdac6
  wangxiyuan authored Aug 13, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  0b1bdac6
- [V1] Add tree drafting tests for eagle spec decoding (#22705) · d94e3026
  Giancarlo Delfin authored Aug 13, 2025
```
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
```
  d94e3026
- [Doc] Add max_lora_rank configuration guide (#22782) · 3f52738d
  633WHU authored Aug 13, 2025
```
Signed-off-by: chiliu <cliu_whu@yeah.net>
```
  3f52738d
- [Bugfix] Fix Nemotron VL image processing (#22739) · a01e0018
  Duc-Viet Hoang authored Aug 13, 2025
```
Co-authored-by: ducviet00-h2 <viet.d.hoang@h2corporation.jp>
```
  a01e0018
- [Model] Add missing prefix to glm4_1v (#22716) · 9e7e5baa
  Yuxuan Zhang authored Aug 13, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
  9e7e5baa
- [Model] Add option to run Step3VisionEncoder in DP (#22697) · d16aa3da
  zzh142857 authored Aug 13, 2025
```
Signed-off-by: zzh142857 <chaorenzhaozhenghao@gmail.com>
```
  d16aa3da
- [gpt-oss] upgrade gpt-oss to v0.0.3 and add version check (#22768) · 6807af8f
  Chen Zhang authored Aug 12, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  6807af8f
- [Perf] Support topk softmax fused kernel for broader num_experts (#22211) · 4c558cf6
  shixianc authored Aug 12, 2025
```
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
```
  4c558cf6
- [Bug] Fix Unexpected Keyword Argument 'w1_bias' (#22757) · 77a6bf07
  Wentao Ye authored Aug 13, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  77a6bf07
- Remove unneeded ROCm platform import when using CUDA (#22765) · 4082338a
  Michael Goin authored Aug 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  4082338a
- Force TRTLLM attention for gpt-oss on SM100 (#22678) · c6b92879
  Michael Goin authored Aug 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c6b92879
- [Bugfix] Fix default enable for CUTLASS MLA on SM100 (#22738) · b1361c72
  Michael Goin authored Aug 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  b1361c72
- Fix cuda illegal mem access with Llama4 TP8 + rms_norm custom op (#22701) · 4f0f844b
  Po-Han Huang (NVIDIA) authored Aug 13, 2025
```
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
```
  4f0f844b
- [V0 Deprecation] Remove args for multi-step scheduling (#22779) · c5830381
  Woosuk Kwon authored Aug 12, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  c5830381
- [Misc] Remove tests/multi_step/__init__.py (#22778) · d31f97cf
  Woosuk Kwon authored Aug 12, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  d31f97cf
- [V0 Deprecation] Remove multi-step scheduling (#22138) · 71683ca6
  Woosuk Kwon authored Aug 12, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  71683ca6
- Add hardware plugins to installation doc (#22732) · e1885929
  Michael Goin authored Aug 12, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e1885929
- [Model] Decouple glm4v (#22751) · fde0b611
  Jee Jee Li authored Aug 13, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  fde0b611
- Fix Transformers backend tensor parallel for multimodal models (#22673) · d0a63015
  Harry Mellor authored Aug 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d0a63015
- [Docs] Hide the navigation and toc sidebars on home page (#22749) · 45c3936e
  Harry Mellor authored Aug 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  45c3936e
12 Aug, 2025 18 commits
- [Bugfix] Bump DeepGEMM Version to Fix SMXX Layout Issues (#22606) · ba81acbd
  Frank Wang authored Aug 12, 2025
```
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
```
  ba81acbd
- [Misc] parametrize 'dtype' in test_flash_mla (#22641) · 53c73028
  RUTHLESS-BOT authored Aug 13, 2025
```
Signed-off-by: RUTHLESS-BOT <wujiafeng@cmbchina.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  53c73028
- Fix torch version check for SM100 mxfp4 (#22535) · 6534d2fc
  zifeitong authored Aug 12, 2025
```
Signed-off-by: Zifei Tong <zifeitong@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  6534d2fc
- [CI][Nixl] Check kv cache layout during handshake (#22745) · 422f22e0
  Nicolò Lucchesi authored Aug 12, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  422f22e0
- [Kernel][AMD] Avoid D2H copy and cumsum kernel (#22683) · 6bd8ebf0
  Xiaozhu Meng authored Aug 12, 2025
```
Signed-off-by: Xiaozhu <mxz297@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  6bd8ebf0
- [Chore] Update CODEOWNERS to include @yewentao256 for CUDA kernels, attention... · dab4f9f7
  Wentao Ye authored Aug 12, 2025
```
[Chore] Update CODEOWNERS to include @yewentao256 for CUDA kernels, attention backends, quantization, and related tests (#22741)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  dab4f9f7
- Add more test scenario for tensor schema (#22733) · c42fe0b6
  TeeKen Lau authored Aug 13, 2025
```
Signed-off-by: teekenl <teekenlau@gmail.com>
```
  c42fe0b6
- Add: `SupportsEagle3` interface for explicit EAGLE3 support (#22642) · 5a4b4b37
  Rahul Tuli authored Aug 12, 2025
```
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
```
  5a4b4b37
- [Benchmark] Fix terminal colors in benchmark_serving_multi_turn (python 3.12) (#22730) · e5d3d63c
  Daniel Serebrenik authored Aug 12, 2025
```
Signed-off-by: daniels <daniels@pliops.com>
```
  e5d3d63c
- [Bugfix][CI] Fix `test_remote_decode_lifecycle.py::test_short_prompt_lifecycle` (#22727) · 3d9d40ef
  Nicolò Lucchesi authored Aug 12, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  3d9d40ef
- Fix Llama4 FlashInfer FP4 MoE issues (#22511) · 67c153b8
  Po-Han Huang (NVIDIA) authored Aug 12, 2025
```
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
```
  67c153b8
- [CI Failure] fix tests/entrypoints/openai/test_skip_tokenizer.py (#22708) · f7ad6a1e
  wang.yuqi authored Aug 12, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  f7ad6a1e
- Officially support SmolLM3 using the Transformers backend (#22665) · 80bb1e8a
  Harry Mellor authored Aug 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  80bb1e8a
- [BugFix][Nixl][PD] Fix heterogenous TP (#22663) · d030b015
  Nicolò Lucchesi authored Aug 12, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  d030b015
- [Docs] Improve docs navigation (#22720) · 767e63b8
  Harry Mellor authored Aug 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  767e63b8
- [gpt-oss] Enable gpt-oss on ampere (#22714) · 007dd908
  Yongye Zhu authored Aug 12, 2025
```
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
```
  007dd908
- [Misc] remove GH discussions link (#22722) · b8a9d0e4
  Jee Jee Li authored Aug 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  b8a9d0e4
- [LMCache][Example] Align the PYTHONHASHSEED for prefillers and decoders for KV... · 50f2aae1
  zejunchen-zejun authored Aug 12, 2025
```
[LMCache][Example] Align the PYTHONHASHSEED for prefillers and decoders for KV chunks hashing (#21161)
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
```
  50f2aae1