Commits · 3f5a4b6473ad1948ec49d62abf2af48c7dc1c5c6 · OpenDAS / vllm_cscc

"vllm/config/__init__.py" did not exist on "7e7eae338d2774f90ba4b5a04d6c53e7299f40de"

05 Nov, 2025 7 commits
- [Bugfix] Validate custom logits processor xargs for online serving (#27560) · 3f5a4b64
  Isotr0py authored Nov 06, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3f5a4b64
- [ROCm][MLA] Support block-size > 1 for AITER MLA backend (#27224) · 6cae1e53
  Pleaplusone authored Nov 05, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>
```
  6cae1e53
- [BugFix] Support EP/DP + EPLB with MTP (#25311) · e50c4546
  Ilya Markov authored Nov 05, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
```
  e50c4546
- [DCP] check return_lse for all layers in dcp (#27929) · 5d16d0fa
  Chen Zhang authored Nov 05, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  5d16d0fa
- [bugfix] fix wrong `dcp_local_seq_lens` calc (#27518) · 16b37f31
  Qiu authored Nov 05, 2025
```
Signed-off-by: Qiu <qiuchunshuo@huawei.com>
```
  16b37f31
- [BugFix] Fix DCP Assert (AssertionError: DCP not support reorder_batch_threshold > 1 now.) (#28100) · d43ad5a7
  Lucas Wilkinson authored Nov 05, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  d43ad5a7
- [XPU] Add gpt-oss model support for Intel GPU (#27786) · 18b39828
  Kunshang Ji authored Nov 05, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  18b39828
04 Nov, 2025 9 commits
- [ROCm][Perf] New design on ROCm AITER MHA backend Implementation (#25763) · dc937175
  Pleaplusone authored Nov 05, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  dc937175
- [AsyncScheduling] Don't schedule past request max_tokens (#27922) · 938a8169
  Nick Hill authored Nov 04, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  938a8169
- [PerfFix] Avoid separate thread for MP executor shm spin (#28012) · c9f66da8
  Nick Hill authored Nov 04, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  c9f66da8
- [model] Add support for openPangu_Ultra_MoE (#27521) · 05cae69f
  yt0428 authored Nov 05, 2025
```
Signed-off-by: yuantao <2422264527@qq.com>
Signed-off-by: yt0428 <51468697+yt0428@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  05cae69f
- [BugFix] Fix incorrect preallocated sampled_token_ids tensor size (#28025) · 5a0a6dfd
  Nick Hill authored Nov 04, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  5a0a6dfd
- [Core] Enable StatLogger in LLMEngine (#28020) · 300a2659
  Zhuohan Li authored Nov 04, 2025
```
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
```
  300a2659
- [KV Connector] Make KVCacheConfig an explicit constructor argument (#27887) · 58279c60
  Mark McLoughlin authored Nov 04, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  58279c60
- [Bug] Batch invariant: Fix flash attn MLA `RuntimeError: scheduler_metadata... · 7e4be741
  Wentao Ye authored Nov 04, 2025
```
[Bug] Batch invariant: Fix flash attn MLA `RuntimeError: scheduler_metadata must have shape (metadata_size)` (#27884)
```
  7e4be741
- [Metrics] Enable sleep state metric outside of dev mode (#27867) · 380ba681
  Mark McLoughlin authored Nov 04, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  380ba681
03 Nov, 2025 4 commits
- [Bugfix] change FlashMLA reorder_batch_threshold (#27777) · 145c00a4
  Matthew Bonanni authored Nov 03, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  145c00a4
- [Spec Decode] Integrate Suffix Decoding from Arctic Inference (#25784) · 2c19d967
  Aurick Qiao authored Nov 03, 2025
```
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
```
  2c19d967
- [Hybrid] Pass kernel block size to builders (#27753) · 18961c5e
  Thomas Parnell authored Nov 03, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  18961c5e
- [BugFix][LoRA] use adapter_id instead of id field of lora_request (#27728) · 1bf43ae3
  Biswa Panda authored Nov 02, 2025
```
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
```
  1bf43ae3
02 Nov, 2025 1 commit
- [V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377) · 00b31a36
  Asaf Joseph Gardin authored Nov 02, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  00b31a36
01 Nov, 2025 4 commits
- [BugFix] Fix mixed penalties batch with async scheduling (#27910) · c2ed069b
  Nick Hill authored Nov 01, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  c2ed069b
- [Bugfix] DeepSeek V3.2 MTP metadata & CUDA graph issues (#26779) · d811b442
  Haco authored Nov 01, 2025
```
Signed-off-by: xiaohajiayou <923390377@qq.com>
```
  d811b442
- [V0 deprecation] Remove VLLM_USE_V1 usage in platform and v1 module (#27798) · 30a14b03
  wangxiyuan authored Nov 01, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  30a14b03
- [Core] Async scheduling + structured outputs compatibility (#26866) · 0cdbe7b7
  Nick Hill authored Oct 31, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  0cdbe7b7
31 Oct, 2025 6 commits
- [Hybrid] A simpler algorithm to find kernel_block_size (#26476) · df334868
  Chen Zhang authored Oct 31, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  df334868
- Add FLASHINFER_MLA to test_mla_backends and add B200 CI run (#27663) · f29aeb5a
  Matthew Bonanni authored Oct 31, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  f29aeb5a
- [Bugfix] Missing NIXL metadata for handshake initialization if instance spans multi-node (#26338) · d6517be3
  GuanLuo authored Nov 01, 2025
```
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  d6517be3
- [Bugfix] Allow 64-bit integer values for LoRA IDs to avoid overflow/truncation (#27876) · 675704ac
  Madeesh Kannan authored Oct 31, 2025
```
Signed-off-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
```
  675704ac
- [BugFix] Don’t compute reorder threshold when there are no attention groups (#27861) · 933cdea4
  Huamin Li authored Oct 31, 2025
  
  933cdea4
- [Bugfix] Avoid too small block m/n for FlexAttention kernel option (#27853) · 3933f18a
  Isotr0py authored Oct 31, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3933f18a
30 Oct, 2025 9 commits
- [BugFix] Fix broken import in initialize_ray_cluster() (#27838) · c9791f18
  Nick Hill authored Oct 30, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  c9791f18
- [Core][Perf] Only invoke save_new_computed_blocks when computed blocks are not empty (#27799) · 4b68c4a5
  Jialin Ouyang authored Oct 30, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  4b68c4a5
- [Fix] Skip `record_sleep_state` logic in `PrometheusStatsLogger` if not in dev mode (#27789) · 49170025
  Sumanth R Hegde authored Oct 30, 2025
```
Signed-off-by: SumanthRH <sumanthrh99@gmail.com>
```
  49170025
- [Core][Bookkeeping] Update cu_num_accepted_tokens for all req_index (#27629) · 4574d48b
  Jialin Ouyang authored Oct 30, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  4574d48b
- [Bugfix] Fix 2 precommit issues - (mamba_block_size, kv_cache_config) (#27811) · ab98f655
  Tyler Michael Smith authored Oct 30, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  ab98f655
- [Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for... · 60f76baa
  Ilya Markov authored Oct 30, 2025
```
[Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for device selection on cuda-like devices (#27564)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  60f76baa
- [KV offload] Enable CPU KV offload on CUDA alike Platforms (#27770) · 0fe01404
  Zhewen Li authored Oct 30, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  0fe01404
- [Model] Introduce Kimi Linear to vLLM (#27809) · 4e68cc9b
  Zhiyuan Li authored Oct 30, 2025
```
Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>
```
  4e68cc9b
- [Bugfix] Improve GPU validation logging in Ray fallback scenarios (#25775) · 74374386
  Sairam Pillai authored Oct 30, 2025
```
Signed-off-by: Sairam Pillai <sairam.pillai61@gmail.com>
```
  74374386