Commits · f4ee2c3d908ade890bc2e42945d307bc2c341b59 · OpenDAS / vllm_cscc

18 Dec, 2025 5 commits
- [ROCm][Bugfix] fix(structured_output): Skip guidance backend for schemas with... · be2ad5f9
  Andreas Karatzas authored Dec 18, 2025
```
[ROCm][Bugfix] fix(structured_output): Skip guidance backend for schemas with patternProperties (#30730)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  be2ad5f9
- [Fix][FlexAttention] return max logical block index to handle reused blocks (#30915) · 11a89cf9
  Yifan Qiao authored Dec 17, 2025
```
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
```
  11a89cf9
- [ROCm][CI] Reduce Flakiness For test_async_scheduling Using ROCM_ATTN With FP32 (#30811) · fd8afdf3
  Micah Williamson authored Dec 17, 2025
```
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
  fd8afdf3
- [Metrics] Model FLOPs Utilization estimation (#30738) · a0b782f9
  SungMinCho authored Dec 17, 2025
```
Signed-off-by: SungMinCho <tjdals4565@gmail.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  a0b782f9
- [v1] Add PrefixLM support to TritonAttention backend (#30386) · 74a1ac38
  Isotr0py authored Dec 18, 2025
  
  74a1ac38
17 Dec, 2025 4 commits
- [Attention] Update tests to remove deprecated env vars (#30563) · 7eb6cb6c
  Matthew Bonanni authored Dec 17, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  7eb6cb6c
- [Chore] Factor out logic for requesting initial memory (#30868) · 2497228a
  Cyrus Leung authored Dec 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  2497228a
- [Fix] uniform decode batch check (#30747) · 6e9dbcc5
  Jialin Ouyang authored Dec 17, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  6e9dbcc5
- Fix lazy import (#30858) · fb980eb2
  Harry Mellor authored Dec 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb980eb2
16 Dec, 2025 8 commits
- [Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475) · f5f51e59
  Roger Wang authored Dec 16, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
```
  f5f51e59
- [Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) · 9fec0e13
  Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
```
  9fec0e13
- Update where `bytes_to_unicode` is imported from (#30771) · e1625498
  Harry Mellor authored Dec 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e1625498
- [BugFix] Fix memory spike in workspace allocation (#30744) · 00a8d762
  Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  00a8d762
- [Bugfix] Whisper fix number of allocated CrossAttn blocks per-request (#30772) · 75eb302a
  Nicolò Lucchesi authored Dec 16, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  75eb302a
- [ROCm][MTP] Support MTP for AITER MLA backend (#28624) · 9dbbc59b
  Pleaplusone authored Dec 16, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  9dbbc59b
- [Bugfix] Fix RequestOutput miss lora_request (#30636) · 0e391e75
  Jee Jee Li authored Dec 16, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  0e391e75
- [feature] extend DBO to XBO (#30120) · b9ff4f2a
  jiangkuaixue123 authored Dec 16, 2025
```
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
```
  b9ff4f2a
15 Dec, 2025 2 commits

Update batch invariant to use attention config (#30704) · 60dbf7d8

Matthew Bonanni authored Dec 15, 2025


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

60dbf7d8

[Bugfix] Fix deepseek_v32 tokenizer_mode (#30658) · a524d1ba
Jee Jee Li authored Dec 15, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
a524d1ba

14 Dec, 2025 3 commits

CPU KV Offloading: Use more CUDA streams (#29013) · 174e39ea
Or Ozeri authored Dec 15, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
174e39ea

fix: Update json features supported by xGrammar (#30390) · 06089365

Johannes F authored Dec 14, 2025

Signed-off-by: Johannes Flommersfeld <johannes.flommersfeld@tngtech.com>
Signed-off-by: Johannes F <johannesflommersfeld@users.noreply.github.com>
Co-authored-by: Johannes Flommersfeld <johannes.flommersfeld@tngtech.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

06089365

[main][BugFix] Fixed an accuracy bug of Qwen3-next-MTP when batched inferring (#30632) · add1b9d3
drslark authored Dec 14, 2025
```
Signed-off-by: drslark <slarksblood@qq.com>
```
add1b9d3

13 Dec, 2025 7 commits
- [Logs] Optimize startup logs 4 (#29903) · 6e78ed6b
  Wentao Ye authored Dec 13, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  6e78ed6b
- [Doc] Add documents for multi-node distributed serving with MP backend (#30509) · 7c16f3fb
  Isotr0py authored Dec 14, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  7c16f3fb
- [Refactor] `TokenizerRegistry` only uses lazy imports (#30609) · 39cefbdf
  Cyrus Leung authored Dec 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  39cefbdf
- [Chore] Adjust tokenizer import to avoid circular imports (#30601) · 64251f48
  Cyrus Leung authored Dec 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  64251f48
- [Scheduer] Simplify stop checking for pooling models (#30591) · 1cec5b7e
  Nick Hill authored Dec 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  1cec5b7e
- [Bugfix] Dictionary MM embeddings for online chat (#30507) · b09806e2
  Cyrus Leung authored Dec 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b09806e2
- [Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484) · 4fa7ce46
  Roberto L. Castro authored Dec 13, 2025
```
Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  4fa7ce46
12 Dec, 2025 5 commits
- [CI] Fix mypy for vllm/v1/executor (#30517) · 02a58803
  Wentao Ye authored Dec 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  02a58803
- [bugfix] fix bug when top_logprobs=0 with spec decoding (#30059) · d2c919dc
  realliujiaxu authored Dec 13, 2025
```
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
```
  d2c919dc
- [Kernel] Support CUDA Graphs in 3D Triton Attention Kernel (#28306) · 9c0ee995
  jvlunteren authored Dec 12, 2025
```
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
Signed-off-by: jvlunteren <161835099+jvlunteren@users.noreply.github.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  9c0ee995
- [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) · 3e41992f
  Lucas Wilkinson authored Dec 12, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  3e41992f
- [Core] Refactor `_build_attention_metadata` (#29628) · 042da732
  Lucas Wilkinson authored Dec 11, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  042da732
11 Dec, 2025 6 commits
- [Core] Whisper Enable Encoder Batching (#29421) · 0efd9f86
  Nicolò Lucchesi authored Dec 11, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  0efd9f86
- [BugFix][MM]support VLLM_RANDOMIZE_DP_DUMMY_INPUTS (#30472) · 90d6cf92
  Xingyu Liu authored Dec 11, 2025
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  90d6cf92
- [ROCm][Bugfix] Add MLACommonMetadata to allowed attention types for speculative decoding (#30430) · 72aaac5b
  Andreas Karatzas authored Dec 11, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  72aaac5b
- [KVConnector] Add KV events to KV Connectors (#28309) · f4417f84
  Martin Hickey authored Dec 11, 2025
```
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
```
  f4417f84
- [Misc][PCP&DCP] relocate PCP feature check (#30050) · a11f4a81
  Qiu authored Dec 11, 2025
```
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  a11f4a81
- [perf] Use direct copy (broadcast) instead of cat for k_nope/k_pe in MLA prefill (#29710) · fba89069
  Ming Yang authored Dec 11, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  fba89069