[Bugfix][Core] Emit --no-{key} for false BooleanOptionalAction flags in YAML config (#51573)

Raj Vijay Firke committed 3 months ago

[Bugfix][Model] Fix Qwen3.5 MTP for text-only checkpoints (#50734)

efschu committed 3 months ago

[Doc] Add Crusoe Managed Inference deployment guide (#49353)

Emmanuel Acheampong committed 3 months ago

[CI][XPU] Add VLLM_DISABLE_COMPILE_CACHE=1 for other random failed cases in Intel GPU CI (#51604)

xiangdong committed 3 months ago

[V1][Scheduler] Apply Mamba alignment before encoder caps (#51603)

Jiangyun Zhu committed 3 months ago

[XPU] bump up xpu kernel to v0.1.12.3 (#50441)

Kunshang Ji committed 3 months ago

[CI] Upgrade huggingface-hub to 1.27.0 (#51422)

Andreas Karatzas committed 3 months ago

Fix Gemma 4 for upcoming Transformers version (#49797)

Harry Mellor committed 3 months ago

[KV Connector] Canonical CPU layout for parallelism-agnostic KV offload (#48414)

Itay Etelis committed 3 months ago

[ROCm][CI] Extend ROCm AITER MHA (FA) coverage (#40958)

Andreas Karatzas committed 3 months ago

[Bugfix] Fix lfm2 tool parser dropping calls with brackets or newline… (#48171)

Zetian Li - ikun committed 3 months ago

[EC Connector] Call to EC Connector update_connector_output from scheduler (#49579)

omerpaz95 committed 3 months ago

`[Model][Quantization] Add Ling-3.0-flash-fp8 support` (#51265)

zexplorerhj committed 3 months ago

[Bugfix][Quantization] Fix fp32 weight scale for mxfp4 quantization and per-expert checkpoint mapping (#51419)

Isotr0py committed 3 months ago

[CPU] Enable GPTQ and AWQ quantization for s390x (#51148)

Rehan Khan committed 3 months ago

[CPU] Restore linear dispatch for small unquantized GEMMs (#51379)

Li, Jiang committed 3 months ago

Add tiering offloading metrics (#48798)

Srinivas Krovvidi committed 3 months ago

[BugFix] Use file:// rendezvous for single-node executors to eliminate startup port races (#50999)

aoshen02 committed 3 months ago

[Bugfix][Parser] Emit REASONING_END for Inkling tool calls that follow no thinking block (#50528)

Jason committed 3 months ago

[Kernel][XPU] Tensor-descriptor operand loads for Triton W8A8 scaled_mm (#47205)

Lena Onyshchenko committed 3 months ago