Commits · 9f6d9dd371c63154dddd2a8b85d7f337f3e10911 · OpenDAS / vllm_cscc

"tools/vscode:/vscode.git/clone" did not exist on "8d75f22e79656dddc975c73133fdccbbebc5c963"

20 Mar, 2026 16 commits
- [UX] Enable torch_profiler_with_stack (#37571) · dd20ee4e
  Jee Jee Li authored Mar 20, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  dd20ee4e
- [Misc] Use logger.info_once for auto tool choice log message (#37661) · 0523449c
  Chauncey authored Mar 20, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  0523449c
- [Model] Deprecate the score task (this will not affect users). (#37537) · ed359c49
  wang.yuqi authored Mar 20, 2026
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  ed359c49
- [Model Runner V2] Fix draft logits not populated during cudagraph replay (#37639) · dcee9be9
  Giancarlo Delfin authored Mar 20, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  dcee9be9
- [Bug] Fix FlashInfer allreduce fusion workspace uninitialized error (#37461) · 0140eafb
  Wei Zhao authored Mar 20, 2026
```
Signed-off-by: root <root@prenyx0169.a51.clusters.nvidia.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: <>
Co-authored-by: root <root@prenyx0169.a51.clusters.nvidia.com>
Co-authored-by: root <root@prenyx0042.a51.clusters.nvidia.com>
```
  0140eafb
- [PluggableLayer][MM] Add PluggableLayer for CustomQwen2Decoder (#37293) · 0674d1fe
  Wangbei25 authored Mar 20, 2026
```
Signed-off-by: Wangbei25 <wangbei41@huawie.com>
Signed-off-by: Wangbei25 <wangbei41@huawei.com>
Co-authored-by: Wangbei25 <wangbei41@huawie.com>
```
  0674d1fe
- [Model] Refactor Step3-VL processor to HF style (#37579) · 30108fc8
  Cyrus Leung authored Mar 20, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  30108fc8
- [Model Runner V2] fix draft attention metadata generation (#37364) · 39474513
  Giancarlo Delfin authored Mar 19, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  39474513
- fix(xpu): Re-compute compile ranges after platform-specific config updates (#37523) · 638a872d
  Yuxiang Liang authored Mar 20, 2026
```
Signed-off-by: Yuxiang Liang <yuxiang.liang@intel.com>
Signed-off-by: Yuxiang Liang <yuliang@habana.ai>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  638a872d
- [V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612) · 9040151f
  Flora Feng authored Mar 19, 2026
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  9040151f
- [Bugfix][LoRA] Fix Qwen35 LoRA (#36976) · 8fbe3f30
  Jee Jee Li authored Mar 20, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8fbe3f30
- [compile][graph_partition]Add tensor size handling (#36038) · ea2c148f
  Xiao authored Mar 19, 2026
```
Signed-off-by: Xiao Fu <xiaofu@meta.com>
```
  ea2c148f
- [Feat] Enable CompressedTensorW4A8Int for XPU (#37207) · 47b7af0d
  Tianmu Li authored Mar 19, 2026
```
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
```
  47b7af0d
- fix: disambiguate multimodal prefix cache keys (#36708) · 269bf46d
  tianshu-Michael-yu authored Mar 19, 2026
```
Signed-off-by: tianshu.yu <tianshuyu.formal@gmail.com>
```
  269bf46d
- Fix DP coordinator ZMQ port TOCTOU (#37452) · ca1ac1a4
  Itay Alroy authored Mar 20, 2026
```
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
```
  ca1ac1a4
- [ROCm][Bugfix] fix cache block size mismatch for aiter unified attention (#37606) · 4ca3fa6b
  Divakar Verma authored Mar 19, 2026
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  4ca3fa6b
19 Mar, 2026 24 commits

[Bugfix] Fix Deepseekv32 tool parser when stream interval > 1 (#36056) · be12afd2
Flora Feng authored Mar 19, 2026

be12afd2
[Bug] Fix EmbedIOprocessor "classify" <-> "embed" (#37573) · df3c0291
Wentao Ye authored Mar 19, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
df3c0291
[Refactor] Remove dead code in pooling model (#37572) · 2be1a0f7
Wentao Ye authored Mar 19, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
2be1a0f7

Fix AttributeError in Qwen3.5 GDN layers with quantized models (#37448) · 4120a05f

Jim Smith authored Mar 19, 2026


Signed-off-by: Jim Smith <jim@joshua8.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Xin Yang <105740670+xyang16@users.noreply.github.com>

4120a05f

[Performance] Enable Triton autotuning disk cache by default (#37188) · b55156ea
Artem Perevedentsev authored Mar 19, 2026
```
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
```
b55156ea
[MoE Refactor] Rename "naive" all2all backend (#36294) · 91be5f9b
bnellnm authored Mar 19, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
91be5f9b
[MoE Refactor] DefaultMoERunner simplifcation (#33049) · 9279c59a
bnellnm authored Mar 19, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
9279c59a
[Log] Log once in local node by default (#37568) · 74540961
Wentao Ye authored Mar 19, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
74540961
[CI] Add retry with 4x backoff to HTTP fetches for transient failures (#37218) · fb8b5e05
Andreas Karatzas authored Mar 19, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
fb8b5e05
Fix `SpeculatorsConfig` now that `PreTrainedConfig` is a `dataclass` in Transformers (#37574) · e5d96dc8
Harry Mellor authored Mar 19, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
e5d96dc8

[Bugfix] Fix AttributeError when serving MXFP8 models with DeepGEMM installed (#37358) · daa05bf3

EdalatiAli authored Mar 19, 2026


Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

daa05bf3

[torch.compile][BE][Multimodal] Remove requirement to set_model_tag to avoid... · 7769b583

Lucas Kabela authored Mar 19, 2026


[torch.compile][BE][Multimodal] Remove requirement to set_model_tag to avoid cache conflict (#37345)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>

7769b583

[P/D] AnthropicMessages add kv_transfer_params for PD disaggregation (#37535) · 2f9f946b
Chauncey authored Mar 20, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
2f9f946b
[CPU][UX] Do not crash when tcmalloc/libiomp are not ldpreloaded (#37561) · 2890aecc
Fadi Arafeh authored Mar 19, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
2890aecc
[Misc] Cleanup more configs and processors (#37560) · 657855ab
Cyrus Leung authored Mar 19, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
657855ab
[Bug] Fix fp8 trtllm MoE modular kernel supported routing methods (#37346) · e27b8ba3
Wei Zhao authored Mar 19, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
e27b8ba3
[MRV2] Use fp32 for draft logits (#37526) · 40b8363b
Woosuk Kwon authored Mar 19, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
40b8363b
[1/n] Migrate permute_cols to libtorch stable ABI (#31509) · 8b10e4fb
mikaylagawarecki authored Mar 19, 2026
```
Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
```
8b10e4fb

Remove deprecated reasoning_content message field(part-2) (#37480) · 104605cb

Ifta khairul Alam Adil authored Mar 19, 2026


Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Ifta Khairul Alam Adil <ikaadil007@gmail.com>
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Philip Ottesen <phiott256@gmail.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Signed-off-by: Andy Lo <andy@mistral.ai>
Signed-off-by: Thillai Chithambaram <thillaichithambaram.a@gmail.com>
Signed-off-by: sihao.li <sihao.li@intel.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Philip Ottesen <phiott256@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Thillai Chithambaram <79466435+thillai-c@users.noreply.github.com>
Co-authored-by: sihao_li <165983188+1643661061leo@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

104605cb

[LoRA] Minor improvements to LoRA log (#37557) · 96266f11

Jee Jee Li authored Mar 19, 2026


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

96266f11

Cap the number of API servers to 1 when using Elastic EP. (#37466) · 7c0cf3bc
Sage Moore authored Mar 19, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
7c0cf3bc
Stop bench CLI from recursively casting all configs to `dict` (#37559) · 572b4329
Harry Mellor authored Mar 19, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
572b4329
[Misc] Clean up processing logic (#37541) · 9515c208
Cyrus Leung authored Mar 19, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
9515c208
[Bugfix] Add Kimi-K2.5 reasoning/tool parser aliases and tool_call_id support (#37438) · c63ca2b2
DorBernsohn authored Mar 19, 2026
```
Signed-off-by: DorBernsohn <dor.bernsohn@gmail.com>
```
c63ca2b2