Commits · 431535b522c62f1422848e22dfd83bec2d04111a · OpenDAS / vllm_cscc · GitLab

19 Sep, 2025 18 commits
- Enable modelopt gemma3 nvfp4/fp8, make workflow more robust (#22771) · 431535b5
  Zhiyu authored Sep 19, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  431535b5
- [Frontend] Responses API messages out, just harmony for now (#24985) · e69e0b8b
  Alec S authored Sep 19, 2025
```
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  e69e0b8b
- Optimize triton unified attention performance for sliding window attention (#24390) · a2a5f79e
  qizixi authored Sep 19, 2025
```
Signed-off-by: zixi-qi <qizixi@meta.com>
```
  a2a5f79e
- [KV offload][4/N] Offloading KV connector (#22595) · c59a0eca
  Or Ozeri authored Sep 19, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  c59a0eca
- [Core][Prefix Hash] Fix prefix hash metrics sliding window maintainance (#24990) · 2506ce51
  Jialin Ouyang authored Sep 19, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  2506ce51
- [CI/Build] fix test function_calling (#25072) · 47fd08aa
  Chauncey authored Sep 20, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  47fd08aa
- Encoder model support for the Transformers backend (#25174) · 12aed7e4
  Harry Mellor authored Sep 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  12aed7e4
- [Core] Modify the initialization parameters of the lora manager (#25249) · 28219864
  Jee Jee Li authored Sep 20, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  28219864
- [Frontend] Pass API server count to each process (#23717) · 6c117cff
  Cyrus Leung authored Sep 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  6c117cff
- [KV offload][3/N] Add worker-side CPU support (#21448) · 7ac67ea5
  Or Ozeri authored Sep 19, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  7ac67ea5
- Move `ModelConfig` from `config/__init__.py` to `config/model.py` (#25252) · aed16879
  Harry Mellor authored Sep 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  aed16879
- [P/D][Nixl] Introduce `KVTransferMetrics` and aggregation strategy (#22188) · a3d087ad
  Nicolò Lucchesi authored Sep 19, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  a3d087ad
- Move `PoolerConfig` from `config/__init__.py` to `config/pooler.py` (#25181) · 058525b9
  Harry Mellor authored Sep 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  058525b9
- [Kernel][Performance] Add Triton kernel for Qwen3-VL interleaved MRoPE (#25055) · cea91a32
  Isotr0py authored Sep 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cea91a32
- [Misc] Cleanup test conftest for deprecated encoder-decoder models (#25231) · f2718d29
  Isotr0py authored Sep 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  f2718d29
- [gpt-oss] Add ResponseReasoningPartAddedEvent, ResponseReasoningPartDoneEvent... · 6d8246aa
  Andrew Xia authored Sep 18, 2025
```
[gpt-oss] Add ResponseReasoningPartAddedEvent, ResponseReasoningPartDoneEvent for streaming (#24938)
Signed-off-by: Andrew Xia <axia@meta.com>
```
  6d8246aa
- [KV offload][2/N] Introduce LRU-based CPU offloading management (#20075) · 9d1c50a5
  Or Ozeri authored Sep 19, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  9d1c50a5
- [CORE] Prompt Embeddings Support for v1 Engine (#24278) · 9a4600e4
  Andrew Sansom authored Sep 18, 2025
```
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Andrew Sansom <qthequartermasterman@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  9a4600e4
18 Sep, 2025 17 commits
- [KV offload][1b/N] rename offloading to kv_offload (#25191) · a53ad626
  Or Ozeri authored Sep 18, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  a53ad626
- [V0 Deprecation] Remove AsyncLLMEngine (#25025) · e19bce40
  Woosuk Kwon authored Sep 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  e19bce40
- [KV offload][1/N] Introduce an offloading component (#19848) · 505805b6
  Or Ozeri authored Sep 18, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  505805b6
- [New Model] Support BertForTokenClassification / Named Entity Recognition (NER) task (#24872) · 5f696c33
  wang.yuqi authored Sep 18, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  5f696c33
- [Kernel] Decouple Tile Size from Block Size in Triton Unified Attention Kernel (#21197) · 01a583fe
  jvlunteren authored Sep 18, 2025
```
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
```
  01a583fe
- [Misc] Clean up flags in `vllm bench serve` (#25138) · 21da7334
  Roger Wang authored Sep 18, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  21da7334
- [Bugfix][Mamba] - Fix Conv State Kernel FP32 Support (#24883) · 66072b36
  Asaf Joseph Gardin authored Sep 18, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  66072b36
- [Frontend] Support setting logprobs to -1 (#25031) · cc935fdd
  Chauncey authored Sep 18, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  cc935fdd
- [Chore] Cleanup guided namespace, move to structured outputs config (#22772) · 29283e89
  Aaron Pham authored Sep 18, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  29283e89
- Add 'path' option to ImagePrompt data_format (#25081) · aa3f105c
  Gerard Finol authored Sep 18, 2025
```
Signed-off-by: Gerard Finol <gerard.finol@urv.cat>
```
  aa3f105c
- [Spec Decode] Efficient padded speculation (#24539) · b7433ca1
  Benjamin Chislett authored Sep 18, 2025
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  b7433ca1
- [V0 Deprecation] Remove more V0 tests (#25117) · 5c65a72b
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  5c65a72b
- Mark prompt logprobs as incompatible with prompt embeds at API level (#25077) · bec060fd
  Andrew Sansom authored Sep 17, 2025
```
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
```
  bec060fd
- [V0 Deprecation] Skip PP test (#25128) · 7fb2a5be
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  7fb2a5be
- [V0 Deprecation] Remove misc V0 tests (#25118) · 6c036615
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  6c036615
- [V0 Deprecation] Remove V0 Tracing & Metrics tests (#25115) · 2fc24e94
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2fc24e94
- [V0 Deprecation] Remove V0 Engine tests (#25114) · 2c3c1bd0
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2c3c1bd0
17 Sep, 2025 5 commits
- [Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537) · 5963b98b
  bnellnm authored Sep 17, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  5963b98b
- [Bugfix] Fix accuracy issue for silu_mul + nvfp4 quant fusion kernel (#24833) · e6585ddb
  elvischenv authored Sep 18, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  e6585ddb
- [V1] Logits processor docs (#22919) · 7ae98875
  afeldman-nm authored Sep 17, 2025
```
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
Signed-off-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
Co-authored-by: Joseph Marinier <Joseph.Marinier@gmail.com>
```
  7ae98875
- [CI Bugfix] Fix failing test_model_load_with_params tests due to tokenizer refactor (#25086) · e3db5ebb
  Michael Goin authored Sep 17, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e3db5ebb
- [V0 Deprecation] Remove V0 tests in test_sequence.py (#25088) · 9d442b7c
  Woosuk Kwon authored Sep 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  9d442b7c