Commits · d3af8c18317c0dc008d42e4367fbb9045cfb7bf6 · OpenDAS / vllm_cscc

"tests/vscode:/vscode.git/clone" did not exist on "c36ac98d0118537ec5f3f405a68311a10f9b59a5"

14 Apr, 2026 3 commits

[Core][Metrics][BugFix] Replace num_cached_tokens/num_external_computed_tokens... · d3af8c18

Mark McLoughlin authored Apr 14, 2026


[Core][Metrics][BugFix] Replace num_cached_tokens/num_external_computed_tokens with PrefillStats (#37460)

Related to `Counters can only be incremented by non-negative amounts`
error with the `vllm:prompt_tokens_by_source_total` metric.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Or Ozeri <or@ozery.com>

d3af8c18

Fix Responses API streaming for multiple auto tool calls (#39626) · 25b3242d
noobHappylife authored Apr 14, 2026
```
Signed-off-by: noobhappylife <aratar1991@hotmail.com>
```
25b3242d

[Bugfix] Fix Gemma4 tool parser converting bare `null` to string `"null"` (#39679) · b075604d

김의진 authored Apr 14, 2026


Signed-off-by: KimuGenie <baby11686@naver.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

b075604d

13 Apr, 2026 11 commits
- Bug/test eagle dp v0 (#38938) · 8213e8f8
  Monishver authored Apr 13, 2026
```
Signed-off-by: Monishver Chandrasekaran <monishverchandrasekaran@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  8213e8f8
- [Bugfix][Pooling] Fix silent weight corruption with buffer-reusing iterators (#39650) · 3693f922
  Pedram Razavi authored Apr 13, 2026
```
Signed-off-by: Pedram Razavi <pedram.razavi@gmail.com>
```
  3693f922
- [Core][Metrics] expose waiting request breakdown via labeled metric (capacity/deferred) (#38435) · 5c18b961
  mukesh-hai authored Apr 13, 2026
```
Signed-off-by: Mukesh Baphna <mukesh@hippocraticai.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  5c18b961
- [Bugfix] Use is_integrated to detect UMA GPUs for memory reporting (#35356) · 995e9a20
  haosdent authored Apr 14, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  995e9a20
- [CI][Metrics] Fix local_cache_hit assertion after prompt tokens metrics updates (#39709) · 10d9872d
  zhanqiuhu authored Apr 13, 2026
```
Signed-off-by: ZhanqiuHu <zhu@redhat.com>
```
  10d9872d
- [Bug] Fix TypeError when hf_config.architectures is None during model loading (#38849) · 8d825b87
  Tihomir Elek authored Apr 13, 2026
```
Signed-off-by: Tihomir Elek <tiho.elek@gmail.com>
```
  8d825b87
- [Bugfix] Fix Responses API instructions leaking through previous_response_id (#37727) · 200a727e
  Yufeng He authored Apr 13, 2026
```
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  200a727e
- feat: add max_tokens_per_doc in rerank request. (#38827) · edbc1abd
  Jesus Federico authored Apr 13, 2026
```
Signed-off-by: Jesus Federico <jefp@amazon.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  edbc1abd
- [Bugfix] Fix GLM tool parser streaming with MTP or stream interval (#39253) · 0e39202c
  Flora Feng authored Apr 13, 2026
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  0e39202c
- [LoRA] Support dual CUDA streams-Linear Layer (#35721) · 715681c1
  Jee Jee Li authored Apr 13, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  715681c1
- [Bugfix] [Tests] Enforce `out` tensor device in `kernel/moe/test_cutedsl_moe.py` (#39644) · 620e8924
  Yongye Zhu authored Apr 12, 2026
```
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
```
  620e8924
12 Apr, 2026 5 commits

[compile] Bug fix for _decompose_size_nodes (#38360) · f00c5539
Animesh Jain authored Apr 12, 2026
```
Signed-off-by: Animesh Jain <anijain@umich.edu>
```
f00c5539
fix(moe): fix RoutedExpertsCapturer assertion failure with DP>1 and MK path (#37879) · 21fab0a3
Le Yang authored Apr 12, 2026

21fab0a3

[KVConnector][NIXL] Organize NIXL connector into its own directory (#39354) · 3244a2eb

Nicolò Lucchesi authored Apr 12, 2026



The number of features supported by the connector has grown substantially
and the `nixl_connector.py` file has accumulated a lot of code. Creates a separate
directory and isolates connector/scheduler code in the hope of improving clarity
and maintainability.

Further refactor of components aimed at improving clarity and simplifying code
will follow soon.
Signed-off-by: NickLucche <nlucches@redhat.com>

3244a2eb

[Core][Metrics] Remove `vllm:prompt_tokens_recomputed` metric (#38709) · 72ff142c
Mark McLoughlin authored Apr 12, 2026
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
72ff142c
[HMA] [KVEvent] Enable GPU-side KV events for HMA (#37688) · cc07dad7
Martin Hickey authored Apr 12, 2026
```
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Or Ozeri <or@ozery.com>
```
cc07dad7

11 Apr, 2026 4 commits
- [Quant] add CompressedTensorsW8A8Mxfp8 for linear and MoE layers (#38815) · df1e30e7
  EdalatiAli authored Apr 11, 2026
```
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
```
  df1e30e7
- [Perf] Fuse Zero Initializer for FP8 DeepGemm Block Quant Kernel (#39547) · 59b2f7b6
  Wei Zhao authored Apr 11, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  59b2f7b6
- [Gemma4][Bugfix]: Enable Gemma4ForCasualLM to load lora adapters correctly (#38844) · 92feb999
  ShubyM authored Apr 11, 2026
```
Signed-off-by: ShubyM <shubymishra20@gmail.com>
```
  92feb999
- [XPU] Fix spec-decode UTs under tests/v1/spec_decode (#38491) · 0f3ce4c7
  Yan Ma authored Apr 11, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  0f3ce4c7
10 Apr, 2026 14 commits
- Add structure to `requirements/` directory (#39024) · fc645f1a
  Harry Mellor authored Apr 10, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  fc645f1a
- [Bugfix] Fix FlashInfer crash with kv_cache_dtype_skip_layers (#39002) · e816a881
  yzong-rh authored Apr 10, 2026
```
Signed-off-by: Yifan Zong <yzong@redhat.com>
```
  e816a881
- [CI] Add MultiConnector (Nixl+Offloading) e2e edge case tests (#39343) · e281cb72
  zhanqiuhu authored Apr 10, 2026
```
Signed-off-by: ZhanqiuHu <zhu@redhat.com>
```
  e281cb72
- [Kernel] Porting the TRTLLM minimax_allreduce_rms kernels (#37045) · ecd1ea13
  Jee Jee Li authored Apr 11, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  ecd1ea13
- [New Model]: jinaai/jina-reranker-v3 (#38800) · cb5f7501
  wang.yuqi authored Apr 10, 2026
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  cb5f7501
- [CI] Add Nixl+OffloadingConnector e2e integration tests (#39200) · c9dddc14
  Nicolò Lucchesi authored Apr 10, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  c9dddc14
- [Kernel][Hardware][AMD] Add TritonW4A16LinearKernel for ROCm (#37352) · d468322d
  jatseng-ai authored Apr 10, 2026
```
Signed-off-by: jatseng-ai <jatseng@amd.com>
Signed-off-by: jatseng-ai <janet.tseng@amd.com>
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Matthias Gehre <matthias.gehre@amd.com>
```
  d468322d
- [model] support FireRedLID (#39290) · 967146e7
  PatchyTIS authored Apr 10, 2026
```
Signed-off-by: PatchouliTaisa <patchychen@tencent.com>
Co-authored-by: PatchouliTaisa <patchychen@tencent.com>
```
  967146e7
- [ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205) · 8e8a3bec
  Lalithnarayan C authored Apr 10, 2026
```
Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  8e8a3bec
- [compile] Allow strings in custom ops without regressing compilation times (#38123) · f44afef6
  Richard Zou authored Apr 10, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  f44afef6
- [GGUF] Support non-standard quant types with prefix (e.g. UD-IQ1_S) (#39471) · 447ce222
  Injae Ryou authored Apr 10, 2026
```
Signed-off-by: Injae Ryou <injaeryou@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  447ce222
- Add platform manual_seed_all API (#38468) · ec68d53b
  Yan Ma authored Apr 10, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  ec68d53b
- Add EXAONE-4.5 (#39388) · e7a1387e
  Kyungmin Lee authored Apr 10, 2026
```
Signed-off-by: lkm2835 <lkm2835@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  e7a1387e
- [Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214) · ecbfbb8d
  Chauncey authored Apr 10, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  ecbfbb8d
09 Apr, 2026 3 commits

[ASR] Fix spacing bw chunks in multi chunk audio transcription (#39116) · f7cad674
Ekagra Ranjan authored Apr 09, 2026
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
```
f7cad674
[Quantization] Support Quark W8A8 INT8 MoE inference (#36320) · 827268e9
PikaPikachu authored Apr 10, 2026
```
Signed-off-by: kangletian <Letian.Kang@amd.com>
```
827268e9

[Performance Improvement] Update `batched_count_greater_than` to handle batch... · a8c6ee9b

Lucas Kabela authored Apr 09, 2026


[Performance Improvement] Update `batched_count_greater_than` to handle batch size 1 without recompile (#38933)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

a8c6ee9b