Commits · 14fdd21d39b634b4c13f7aadbe60e83080b59ebd · OpenDAS / vllm_cscc · GitLab

18 Jun, 2025 13 commits
- [Core] More fixes to MultiModalEmbeddings type handling (#19715) · 14fdd21d
  Russell Bryant authored Jun 18, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  14fdd21d
- [Core] Do not copy array during hashing (#19484) · 3b523e38
  Lukas Geiger authored Jun 18, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  3b523e38
- [v1] Support mamba2 (#19327) · a89209b7
  Chen Zhang authored Jun 19, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  a89209b7
- [Bugfix] fix RAY_CGRAPH_get_timeout is not set successfully (#19725) · 12575cfa
  Chauncey authored Jun 19, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  12575cfa
- [Hardware][AMD] integrate aiter chunked prefill into vllm (#18596) · 8b6e1d63
  Zzz9990 authored Jun 18, 2025
```
Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: fsx950223 <fsx950223@outlook.com>
Co-authored-by: charlifu <charlifu@amd.com>
```
  8b6e1d63
- [Platform] Allow platform use V1 Engine by default (#19792) · 257ab954
  wangxiyuan authored Jun 18, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  257ab954
- [Minor] Zero-initialize attn output buffer (#19784) · f04d6045
  Woosuk Kwon authored Jun 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f04d6045
- [V1] Decouple GPU and TPU `InputBatch` (#19778) · 19a53b27
  afeldman-nm authored Jun 18, 2025
```
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
```
  19a53b27
- [V1][P/D] An native implementation of xPyD based on P2P NCCL (#18242) · eccdc831
  Zhonghua Deng authored Jun 18, 2025
```
Signed-off-by: Abatom <abzhonghua@gmail.com>
```
  eccdc831
- [V1] Add API docs for EncoderCacheManager (#19294) · 5f52a846
  Russell Bryant authored Jun 18, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  5f52a846
- [Misc] Add __str__ for RequestStatus (#19780) · d4629dc4
  lkchen authored Jun 17, 2025
```
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  d4629dc4
- [MISC] correct DeviceConfig device field static type analysis (#19699) · 6e9cc73f
  Ning Xie authored Jun 18, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  6e9cc73f
- [MISC] correct copy_blocks src_to_dists param type (#19696) · c53711bd
  Ning Xie authored Jun 18, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  c53711bd
17 Jun, 2025 13 commits
- [Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158) · a44b1c95
  Charlie Fu authored Jun 17, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  a44b1c95
- [Bugfix] Fix faulty triton importing logic when using Ray for DP (#19734) · b447624e
  Michael Goin authored Jun 18, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  b447624e
- [Misc] Update lmcache connector with the latest connector apis (#19441) · cda92307
  Jiayi Yao authored Jun 17, 2025
```
Signed-off-by: YaoJiayi <120040070@link.cuhk.edu.cn>
```
  cda92307
- [Perf] Optimize `moe_align_block_size` CUDA kernel (#19572) · ffb2cd6b
  Wentao Ye authored Jun 17, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  ffb2cd6b
- [Bugfix] Update multimodel models mapping to fit new checkpoint after Transformers v4.52 (#19151) · ca94d7fa
  Isotr0py authored Jun 17, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  ca94d7fa
- [Mis] remove duplicate engine status checks (#19647) · 5a1c2e15
  CYJiang authored Jun 17, 2025
```
Signed-off-by: googs1025 <googs1025@gmail.com>
```
  5a1c2e15
- [V1][Kernel] Flashinfer HND KV cache layout (#19280) · 4c8f64fa
  Nicolò Lucchesi authored Jun 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  4c8f64fa
- [Kernel] Add Split-KV Support to Unified Triton Attention Kernel (#19152) · ccd7c050
  jvlunteren authored Jun 17, 2025
```
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
```
  ccd7c050
- [Core] add remove_seq_from_computed_blocks_tracker to BlockSpaceManager (#19686) · 5c76b9cd
  quanliu authored Jun 17, 2025
```
Signed-off-by: 刘全 <quan.liu2@dbappsecurity.com.cn>
Co-authored-by: 刘全 <quan.liu2@dbappsecurity.com.cn>
```
  5c76b9cd
- Fixes IMA for TP w/ flex-attention (#19712) · ddfed314
  Driss Guessous authored Jun 16, 2025
```
Signed-off-by: drisspg <drisspguessous@gmail.com>
```
  ddfed314
- [DOC] fix doc typos (#19600) · 5b3ad5ec
  Di Liu authored Jun 17, 2025
```
Signed-off-by: Di Liu <liu-di@sjtu.edu.cn>
```
  5b3ad5ec
- [Frontend] add chunking audio for > 30s audio (#19597) · ede5c4eb
  nguyenhoangthuan99 authored Jun 17, 2025
```
Signed-off-by: nguyenhoangthuan99 <thuanhppro12@gmail.com>
```
  ede5c4eb
- [Fix] Fall back to Gloo when NCCL backend is unavailable (#19641) · 0860087a
  Conroy Cheers authored Jun 17, 2025
```
Signed-off-by: conroy-cheers <conroy@corncheese.org>
```
  0860087a
16 Jun, 2025 14 commits
- [Quantization] Remove FP4 emulation; Fall-back to marlin for device < 100 (#19563) · 6bc7b573
  Dipika Sikka authored Jun 16, 2025
  
  6bc7b573
- [V1] Change return type on get_multimodal_embeddings() (#19446) · 90f9c2eb
  Russell Bryant authored Jun 16, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  90f9c2eb
- [Model] Add support for MiniMaxM1ForCausalLM (shares architecture with... · 387bdf0a
  qscqesze authored Jun 17, 2025
```
[Model] Add support for MiniMaxM1ForCausalLM (shares architecture with MiniMaxText01ForCausalLM) (#19677)
Signed-off-by: QscQ <qscqesze@gmail.com>
```
  387bdf0a
- [Kernels] Use empty for modular MoE workspaces (#19667) · 5e5baa91
  bnellnm authored Jun 16, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  5e5baa91
- [Bugfix] fix missing 'finish_reason': null in streaming chat (#19662) · 836d4ce1
  Chauncey authored Jun 16, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  836d4ce1
- [Bugfix] Fix TP inference for Flex attention backend (#19657) · 1173804d
  Isotr0py authored Jun 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  1173804d
- [Feature]:Allow for Granite MoE Hybrid models with _only_ shared experts. (#19652) · 4d542402
  Shawn Tan authored Jun 16, 2025
```
Signed-off-by: Shawn Tan <shawntan@ibm.com>
```
  4d542402
- [BugFix] Don't catch BaseException when dumping execute_model errors (#19626) · ee35e96a
  Nick Hill authored Jun 16, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  ee35e96a
- [Kernel] GGUF MMVQ kernel for multiple input vectors (#18754) · dec66d25
  Szymon Ożóg authored Jun 16, 2025
```
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
```
  dec66d25
- [CI] Add mteb testing for rerank models (#19344) · f40f763f
  wang.yuqi authored Jun 16, 2025
  
  f40f763f
- [MISC] typo fix (#19672) · 26bc46ef
  Ning Xie authored Jun 16, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  26bc46ef
- [TPU] support attention head dim smaller than 128 (#19620) · a77aea59
  Chengji Yao authored Jun 15, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  a77aea59
- [Misc] Fix skipped max-model-len validation when deriving max model length... · b692e9cd
  Ye (Charlotte) Qi authored Jun 15, 2025
```
[Misc] Fix skipped max-model-len validation when deriving max model length from tokenizer config (#19660)
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  b692e9cd
- [Misc][Frontend] passthrough `bad_words` (#19564) · 367871a4
  Francesco Bertolotti authored Jun 16, 2025
```
Signed-off-by: Francesco Bertolotti <francesco.bertolotti@igenius.ai>
Co-authored-by: Francesco Bertolotti <francesco.bertolotti@igenius.ai>
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
```
  367871a4