[P/D][Nixl] Introduce `KVTransferMetrics` and aggregation strategy (#22188)

Nicolò Lucchesi committed about 1 year ago

Move `PoolerConfig` from `config/__init__.py` to `config/pooler.py` (#25181)

Harry Mellor committed about 1 year ago

[Bugfix][Perf] Misc fixes for Qwen3 VL (#25238)

Roger Wang committed about 1 year ago

[Kernel][Performance] Add Triton kernel for Qwen3-VL interleaved MRoPE (#25055)

Isotr0py committed about 1 year ago

[bugfix] fix MHA for models like OpenGVLab/InternVL3_5-38B (#25146)

Yan Ma committed about 1 year ago

[Misc] Cleanup test conftest for deprecated encoder-decoder models (#25231)

Isotr0py committed about 1 year ago

[Bugfix][CPU] Add placeholder to avoid import errors when using fused_moe ops on platforms without triton (#25137)

Li, Jiang committed about 1 year ago

[CPU] Disable oneDNN linear on non-x86 platforms (#25166)

Li, Jiang committed about 1 year ago

[Build] Update Xgrammar to 0.1.24 to get a CVE fix (#25188)

Russell Bryant committed about 1 year ago

[OOT] Support sync_model_loading for OOT (#25126)

Chendi.Xue committed about 1 year ago

[Docs] Fix griffe warnings in vllm/multimodal (#25216)

Michael Yao committed about 1 year ago

[Misc] Clean up MM profiling warnings (#25222)

Roger Wang committed about 1 year ago

[Perf] Optimize memory peak during EAGLE model loading. (#24585)

Chen Ding committed about 1 year ago

[gpt-oss] Add ResponseReasoningPartAddedEvent, ResponseReasoningPartDoneEvent for streaming (#24938)

Andrew Xia committed about 1 year ago

[KV offload][2/N] Introduce LRU-based CPU offloading management (#20075)

Or Ozeri committed about 1 year ago

[CORE] Prompt Embeddings Support for v1 Engine (#24278)

Andrew Sansom committed about 1 year ago

[BugFix] Fix DeepGEMM warmup, no m.weight_scale_inv (#25206)

Lucas Wilkinson committed about 1 year ago

[KV offload][1b/N] rename offloading to kv_offload (#25191)

Or Ozeri committed about 1 year ago

[V0 Deprecation] Remove unused async_timeout.py (#25190)

Woosuk Kwon committed about 1 year ago

[Bug] Fix torch Compilation Cache Hit Error (#25093)

Wentao Ye committed about 1 year ago