[ROCm][CI] Fix Nixl+Offloading PD edge cases on TheRock image (#57249)

Matt committed about 1 month ago

[Rust Frontend] Bump vllm-proto to 0.3.0 (#57233)

Alec committed about 1 month ago

[Bugfix][KV Offload] Compact canonical MLA rows (#56799)

Itay Etelis committed about 1 month ago

[CI] Support `FORCE_COLOR` env var; enable colors in CPU CI output (#56913)

Nick Hill committed about 1 month ago

[EC Connector] Add Metrics Collection (#54960)

omerpaz95 committed about 1 month ago

[Core] Don't issue a blocking collective RPC during engine handshake (#57226)

Oxana Korzh committed about 1 month ago

[Scheduler] Add --max-num-active-seqs to cap RUNNING admission (#56758)

Chuan (Richard) Li committed about 1 month ago

[Test][Core] Add hybrid model prefix cache hit-rate coverage (#57127)

Jiangyun Zhu committed about 1 month ago

Use skip-redaction option for crcr-report (#56532)

Andrey Talman committed about 1 month ago

[Bugfix][Rust Frontend] Accept appended EngineCoreOutput fields (#56533)

Alec committed about 1 month ago

[ROCm][Bugfix] Ignore descales for unquantized AITER caches (#56726)

dongluw committed about 1 month ago

[A2A] Add DeepEPv2 to SP Supported List (#57210)

Robert Shaw committed about 1 month ago

[Rust Frontend] Normalize native renderer reasoning controls (#56998)

Bugen Zhao committed about 1 month ago

[ROCm] triton+triton_kernels 3.8 mxfp4 MoE support (gpt-oss + DeepSeek-V4) (#55934)

Rohan Potdar committed about 1 month ago

[ROCm][CI] Enable AITER FP8/unquantized cases in modular-kernel sweep + fix MoRI per-tensor FP8 dispatch (#57074)

Divakar Verma committed about 1 month ago

[Bugfix][Metrics][MFU] Size activation traffic from the model dtype (#57070)

Thillai Chithambaram committed about 1 month ago

[Bugfix][Spec Decode] Fix EAGLE and dense draft startup with EP (#56930)

kyleliang-nv committed about 1 month ago

[ROCm][CI] Shard MI300 Multimodal Processor (#57056)

Aarushi Jain committed about 1 month ago

[Tests] Delete deprecate torchao tests for v1 configs (#52956)

andrewor14 committed about 1 month ago

[Frontend] Add per-request metrics to Responses API (#55084)

xinnywinne committed about 1 month ago