Commits · 4a79262e0f560c50a9831ee672a853e598047ee5 · OpenDAS / vllm_cscc

23 Apr, 2026 4 commits
- [UT][Hardware] let torchrun example tests use the default backend (#39879) · 4a79262e
  liuzhenwei authored Apr 23, 2026
```
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
```
  4a79262e
- [Misc] Support Human-readable (k/K/m/M..) json cli arg (#40473) · 9c2492e5
  Nicolò Lucchesi authored Apr 23, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  9c2492e5
- [Responses] Add tool_choice/tools validation to match OpenAI behavior (#40399) · 8317cedc
  Flora Feng authored Apr 23, 2026
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  8317cedc
- [TurboQuant] enable FA3/FA4 for prefill paths (#40092) · fe9c3d6c
  Julian Huang authored Apr 23, 2026
```
Signed-off-by: 墨楼 <huangzhilin.hzl@antgroup.com>
Co-authored-by: 墨楼 <huangzhilin.hzl@antgroup.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Codex <codex@openai.com>
```
  fe9c3d6c
22 Apr, 2026 16 commits

[Bugfix] Fix RMS norm + quant fusion on DeepGEMM UE8M0 path for B200 (#40552) · b8401a9b
Lucas Kabela authored Apr 22, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
b8401a9b
[gRPC] Add standard gRPC health checking (grpc.health.v1) for Kubernetes native probes (#38016) · 9c271f94
Honglin Cao authored Apr 22, 2026
```
Signed-off-by: Honglin Cao <Caohonglin317@hotmail.com>
```
9c271f94

[Bugfix][Parser] Fix Mistral pre-v11 tool parser failing on trailing model output (#40531) · cfa49213

Doug Smith authored Apr 22, 2026


Signed-off-by: dougbtv <dosmith@redhat.com>
Signed-off-by: Doug Smith <dougbtv@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>

cfa49213

FlexAttention non-causal support (#40394) · 29f64c5f

Fynn Schmitt-Ulms authored Apr 22, 2026


Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

29f64c5f

Fix test_startup.py for torch 2.12 (#40636) · eb6661d5
Angela Yi authored Apr 22, 2026
```
Signed-off-by: Angela Yi <yiangela7@gmail.com>
```
eb6661d5

[NVFP4] NVFP4 MOE emulation fallback for H100/MI300/MI350, standardize... · d622e27d

fxmarty-amd authored Apr 22, 2026


[NVFP4] NVFP4 MOE emulation fallback for H100/MI300/MI350, standardize `TritonExperts` usage for OCP MX emulation (#35737)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Kyle Sayers <kylesayrs@gmail.com>

d622e27d

[Bugfix][CI] Fix... · 33ef1941

Nicolò Lucchesi authored Apr 22, 2026


[Bugfix][CI] Fix `v1/kv_connector/unit/test_nixl_connector_hma.py::test_fewer_blocks_with_hma` (#40597)
Signed-off-by: NickLucche <nlucches@redhat.com>

33ef1941

[Bugfix] LoRA for DeepSeek V3.2 (#35077) · a250f1bd

ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored Apr 22, 2026


Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

a250f1bd

[Model] Add block-local attention and YaRN for local layers to Gemma3 (#39823) · 12367487
philip-essential authored Apr 21, 2026
```
Signed-off-by: Philip Monk <169196560+philip-essential@users.noreply.github.com>
```
12367487
[fix] flaky test_mla_attn_quant_fusion.py (#40530) · 4254aeb5
Carl Y authored Apr 21, 2026
```
Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
```
4254aeb5

[kv_offload+HMA][8/N]: Support multi-group worker transfer (#38453) · aad88f84

Or Ozeri authored Apr 22, 2026


Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

aad88f84

[compile] mla + group fp8 fusion (#38877) · 4506319a

Carl Y authored Apr 21, 2026


Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

4506319a

[Multimodal] Add PyAV video backend for concurrent video decoding (#39986) · 6f2c71be

Jaseel Muhammad authored Apr 22, 2026


Signed-off-by: Jaseel Muhammad <jaseel.muhammad@mbzuai.ac.ae>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

6f2c71be

[AMD][CI][BugFix] Override normalize_e4m3fn_to_e4m3fnuz for fnuz machines in... · 2463f00f

rasmith authored Apr 21, 2026


[AMD][CI][BugFix] Override normalize_e4m3fn_to_e4m3fnuz for fnuz machines in test_moe_layer_no_parallel (#40550)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>

2463f00f

test: add nan/inf clamp regression test for fused_topk_bias (#40553) · 46794958
Jhao-Ting Chen authored Apr 21, 2026
```
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
```
46794958
[Bugfix] avoid warmup if text only expectation in multi_modal run (#40409) · 6ff8dea0
Khushali Desai authored Apr 21, 2026
```
Signed-off-by: khushali9 <khushali.desai9@gmail.com>
```
6ff8dea0

21 Apr, 2026 13 commits

[Startup][UX] Enable CUDAGraph memory profiling by default (#38284) · 96a85c57
Matthew Bonanni authored Apr 21, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
96a85c57

[MoE Refactor] Add more MoE layer tests (#39349) · 9db4650e

bnellnm authored Apr 21, 2026

Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

9db4650e

[MoE Refactor] Remove SharedFusedMoE class (#35782) · 5e584ce9
bnellnm authored Apr 21, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
5e584ce9
[Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413) · 16688b26
Wentao Ye authored Apr 21, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
16688b26

[Performance] Add is_reasoning_end_streaming() override to GptOssReasoningParser (#35745) · 5544f8c1

Fergus authored Apr 21, 2026


Signed-off-by: Fergus <fergus.barratt00@gmail.com>
Signed-off-by: fergus barratt <fergus.barratt00@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

5544f8c1

Revert #38730 and #38791 (#40032) · 6d85b36a

Vadim Gimpelson authored Apr 21, 2026


Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>

6d85b36a

Add Granite 4.1 Vision as built-in multimodal model (#40282) · d249a9e9

artem-spector authored Apr 21, 2026


Signed-off-by: Artem Spector <artems@il.ibm.com>
Signed-off-by: artemspector <artems@il.ibm.com>
Co-authored-by: artemspector <artems@il.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

d249a9e9

[Frontend] Remove frontend pooling multi task support. (#37861) · d2e2e856

wang.yuqi authored Apr 21, 2026


Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

d2e2e856

feat(multimodal): support externally processed mm_kwargs with cache injection (#39502) · 766cb65d

Kris Hung authored Apr 21, 2026


Signed-off-by: Krish Hung <krishung5@gmail.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

766cb65d

fix: clamp NaN/Inf in topk_softmax to prevent duplicate expert IDs (#39391) · 28c22215
Jhao-Ting Chen authored Apr 21, 2026
```
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
```
28c22215
[Bugfix] Normalize malformed dict prompts that carry token IDs in `prompt` (#40339) · 5a94a198
Zeyu Zhang authored Apr 21, 2026
```
Signed-off-by: Alchuang22-dev <2584829494@qq.com>
```
5a94a198

[Bugfix] Fix `_CONFIG_REGISTRY` types getting wrong config class when on-disk... · 0e884fe6

Misa authored Apr 20, 2026


[Bugfix] Fix `_CONFIG_REGISTRY` types getting wrong config class when on-disk model_type differs (#39554)
Signed-off-by: Misa <misaAle@users.noreply.github.com>
Signed-off-by: Misael Casarez <misacasa@amazon.com>
Co-authored-by: Misael Casarez <misacasa@amazon.com>

0e884fe6

[vLLM IR] Add IR op testing and benchmarking infrastructure (#40167) · fe5c115e

Yanan Cao authored Apr 20, 2026


Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Theresa Shan <Theresa.Shan@amd.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

fe5c115e

20 Apr, 2026 7 commits
- [EPLB] Consolidate is_unchanged/is_received_locally into TransferMetadata (#37341) · 3173441b
  Sage Moore authored Apr 20, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  3173441b
- [Bugfix][CI] Fix `tests/distributed/test_torchrun_example_moe.py` (#40349) · 304d5ba1
  Nicolò Lucchesi authored Apr 20, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  304d5ba1
- Update flashinfer to 0.6.8 (#39959) · 191e3fda
  bai authored Apr 20, 2026
```
Signed-off-by: bai <v@gor.io>
```
  191e3fda
- [EPLB] Refactor Async EPLB synchronization logic (#37601) · 3461c8b0
  Sage Moore authored Apr 20, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  3461c8b0
- [MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949) · 726efe17
  bnellnm authored Apr 20, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  726efe17
- [ROCm] Add MLA dual RMS norm fusion (Q, KV) pass for DeepSeek/Kimi-K2 (#39242) · fb5635d3
  Rita Brugarolas authored Apr 20, 2026
```
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com>
```
  fb5635d3
- [XPU] enable triton attention test on XPU by removing cuda device binding (#39627) · e06de7f0
  Yan Ma authored Apr 20, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  e06de7f0