[Metrics] Enable sleep state metric outside of dev mode (#27867)

Mark McLoughlin committed about 1 year ago

[NIXL][XPU] Pin NIXL version to 0.7.0 (#27849)

liuzhenwei committed about 1 year ago

[Refactor] Lazy import tool_parser (#27974)

Chauncey committed about 1 year ago

[LoRA] Lora shrink swizzle (#27694)

li2haipeng committed about 1 year ago

[Bugfix][ROCm] Fix ViT rotary embeddings for torch.compile compatibility on ROCm (#27748)

vllmellm committed about 1 year ago

Remove the tpu docker image nightly build. (#27997)

QiliangCui committed about 1 year ago

[Bugfix] Fix MoE Routing Simulation (#28002)

Tyler Michael Smith committed about 1 year ago

[Bugfix][plugin] fla crash on plugin (#27322)

Hank_ committed about 1 year ago

Add TP parameter to attention tests (#27683)

Matthew Bonanni committed about 1 year ago

[Docs] add runai_streamer_sharded to LoadConfig (#27937)

Ning Xie committed about 1 year ago

[Bugfix] change FlashMLA reorder_batch_threshold (#27777)

Matthew Bonanni committed about 1 year ago

[Bugfix][Qwen][Multimodal] Move Qwen2_5_vl sdpa to custom op and reenable compile (#27764)

Lucas Kabela committed about 1 year ago

[Feature][Benchmarks] Support `inf` burstiness (#26941)

Sophie du Couédic committed about 1 year ago

[Spec Decode] Integrate Suffix Decoding from Arctic Inference (#25784)

Aurick Qiao committed about 1 year ago

[CI/Testing] Add basic single node dual batch overlap test (#27235)

Lucas Wilkinson committed about 1 year ago

[BUG] Make 'binary' default option for saving torch compile artifacts when using standalone_compile (#27616)

ahao-anyscale committed about 1 year ago

[Bugfix] Skip gs:// model paths for speculator detection (#27846)

pwschuurman committed about 1 year ago

Early exit for MoE LoRA kernels (#27131)

gnovack committed about 1 year ago

[Model] Add PaddleOCR-VL Model Support (#27758)

zhang-prog committed about 1 year ago

[CI/Build] Remove the flaky gpt-oss lora test (#27966)

Jee Jee Li committed about 1 year ago