Commits · f40f763f12c0ffbbc781b0ea23f4b9868db70d21 · OpenDAS / vllm_cscc

16 Jun, 2025 7 commits

[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

[Bugfix][Core] Prefix caching causes incorrect outputs due to outdated... · 92183b41

quanliu authored Jun 16, 2025


[Bugfix][Core] Prefix caching causes incorrect outputs due to outdated ComputedBlocksTracker (#18957)
Signed-off-by: 刘全 <quan.liu2@dbappsecurity.com.cn>
Co-authored-by: 刘全 <quan.liu2@dbappsecurity.com.cn>

92183b41

[Misc] Remove duplicate multiproc method setting for CPU platform (#19649) · a5e7242d
Isotr0py authored Jun 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
a5e7242d

15 Jun, 2025 3 commits
- Enable prefix caching with full cuda graphs (#19617) · 055915e6
  Woosuk Kwon authored Jun 15, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  055915e6
- [Kernel] Raise verbose error and consolidate `num_heads/num_kv_heads` divisibility check (#19339) · 0b73736a
  22quinn authored Jun 14, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  0b73736a
- [Bugfix][2/n] Fix speculative decoding CI - Fix test_ngram_e2e_greedy_correctness (#19644) · ee1531bc
  Lu Fang authored Jun 15, 2025
  
  ee1531bc
14 Jun, 2025 5 commits
- [Fix] Convert kv_transfer_config from dict to KVTransferConfig (#19262) · 08500011
  maobaolong authored Jun 15, 2025
  
  08500011
- [Bugfix] Don't attempt to use triton if no driver is active (#19561) · 861a0a0a
  Konrad Zawora authored Jun 14, 2025
  
  861a0a0a
- [Bugfix] Fix auto dtype casting for BatchFeature (#19316) · 2db9044a
  Isotr0py authored Jun 14, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  2db9044a
- [V1][Metrics] Deprecate metrics with gpu_ prefix for non GPU specific metrics. (#18354) · d1e34cc9
  Saheli Bhattacharjee authored Jun 14, 2025
```
Signed-off-by: Saheli Bhattacharjee <saheli@krai.ai>
```
  d1e34cc9
- [BugFix] Fix DP Coordinator incorrect debug log message (#19624) · bd517eb9
  Nick Hill authored Jun 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  bd517eb9
13 Jun, 2025 11 commits
- [torch.compile] Use custom ops when use_inductor=False (#19618) · aafbbd98
  Woosuk Kwon authored Jun 13, 2025
  
  aafbbd98
- [CUDA] Enable full cudagraph for FlashMLA (#18581) · 3597b06a
  Luka Govedič authored Jun 13, 2025
```
Signed-off-by: luka <luka@neuralmagic.com>
```
  3597b06a
- [Model] Fix minimax model cache & lm_head precision (#19592) · a24cb916
  qscqesze authored Jun 13, 2025
```
Signed-off-by: qingjun <qingjun@minimaxi.com>
```
  a24cb916
- [BugFix] Honor `enable_caching` in connector-delayed kvcache load case (#19435) · 7e8d97dd
  Nick Hill authored Jun 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  7e8d97dd
- [torch.compile] reorganize the cache directory to support compiling multiple models (#19064) · d70bc7c0
  youkaichao authored Jun 13, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  d70bc7c0
- use base version for version comparison (#19587) · ce688ad4
  Boyuan Feng authored Jun 13, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  ce688ad4
- [Fix] The zip function in Python 3.9 does not have the strict argument (#19549) · cefdb996
  汪志鹏 authored Jun 13, 2025
```
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
```
  cefdb996
- [CPU] Refine default config for the CPU backend (#19539) · 64587211
  Li, Jiang authored Jun 13, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  64587211
- [Misc] Correct broken docs link (#19553) · bb4a0dec
  Hyogeun Oh (오효근) authored Jun 13, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  bb4a0dec
- [Bugfix] Fix EAGLE vocab embedding for multimodal target model (#19570) · c68698b3
  qizixi authored Jun 12, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  c68698b3
- [BugFix] : Fix Batched DeepGemm Experts (#19515) · e3b12667
  Varun Sundar Rabindranath authored Jun 12, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  e3b12667
12 Jun, 2025 14 commits
- [V1] Resolve failed concurrent structured output requests (#19565) · c57bb199
  Russell Bryant authored Jun 12, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  c57bb199
- [Bugfix] Enforce contiguous input for dynamic_per_token FP8/INT8 quant (#19452) · a3319f4f
  Michael Goin authored Jun 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a3319f4f
- [Misc] Turn MOE_DP_CHUNK_SIZE into an env var (#19506) · 9d880f59
  Varun Sundar Rabindranath authored Jun 12, 2025
  
  9d880f59
- [Spec Decode][Benchmark] Generalize spec decode offline benchmark to more... · 017ef648
  Ekagra Ranjan authored Jun 12, 2025
```
[Spec Decode][Benchmark] Generalize spec decode offline benchmark to more methods and datasets (#18847)
```
  017ef648
- [torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756) · f98548b9
  Luka Govedič authored Jun 12, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
```
  f98548b9
- Fix TorchAOConfig skip layers (#19265) · 96846bb3
  mobicham authored Jun 12, 2025
```
Signed-off-by: mobicham <hicham@mobiuslabs.com>
```
  96846bb3
- [V1][NixlConnector] Drop `num_blocks` check (#19532) · 1129e2b1
  Nicolò Lucchesi authored Jun 12, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  1129e2b1
- [Quantization] Improve AWQ logic (#19431) · 73e2e011
  Jee Jee Li authored Jun 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  73e2e011
- [Bugfix] Respect num-gpu-blocks-override in v1 (#19503) · c9280e63
  jmswen authored Jun 12, 2025
```
Signed-off-by: Jon Swenson <jmswen@gmail.com>
```
  c9280e63
- [Bugfix][V1] Allow manual FlashAttention for Blackwell (#19492) · af09b3f0
  Michael Goin authored Jun 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  af09b3f0
- [AMD][Kernel][BugFix] fix test_rocm_compressed_tensors_w8a8 for rocm (#19509) · 2e090bd5
  rasmith authored Jun 12, 2025
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  2e090bd5
- [BugFix] Handle missing sep_token for Qwen3-Reranker in Score API (#19522) · 1b0b065e
  wonjun Jang authored Jun 12, 2025
```
Signed-off-by: strutive07 <strutive07@gmail.com>
```
  1b0b065e
- [BugFix] Work-around incremental detokenization edge case error (#19449) · d5bdf899
  Nick Hill authored Jun 11, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d5bdf899
- [Frontend] Improve error message in tool_choice validation (#19239) · 7e3e74c9
  22quinn authored Jun 11, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  7e3e74c9