[BugFix] Remove default multiproc executor `collective_rpc` timeout (#17000)

Nick Hill committed over 1 year ago

Fencing Kernels Tests for enabling on AMD (#16929)

Alexei-V-Ivanov-AMD committed over 1 year ago

Add assertion for no objects while hashing hf_config (#16930)

Richard Zou committed over 1 year ago

[FEAT][ROCm]: Support AITER MLA (#15893)

vllmellm committed over 1 year ago

[frontend] enhance tool_calls type check (#16882)

Reid committed over 1 year ago

[Misc] Add S3 environment variables for better support of MinIO. (#16977)

Chauncey committed over 1 year ago

[BugFix] Pass in correct VLLM config in FlashInfer backend (#13207) (#16973)

Zhengyuan Su (苏政渊) committed over 1 year ago

Improve configs - `SpeculativeConfig` (#16971)

Harry Mellor committed over 1 year ago

[Bugfix] Fix distributed bug again in Qwen2.5-VL & Qwen2.5-Omni (#16974)

Yang Fan committed over 1 year ago

[Misc] refactor example series (#16972)

Reid committed over 1 year ago

[FEAT][ROCm] Integrate Paged Attention Kernel from AITER (#15001)

vllmellm committed over 1 year ago

[Doc] Improve documentation for multimodal CLI args (#16960)

Cyrus Leung committed over 1 year ago

[BugFix] Fix incremental detokenization perf issue (#16963)

Nick Hill committed over 1 year ago

[Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation - BitBLAS (#6036)

Lei Wang committed over 1 year ago

[V1] Remove pre-allocation for KV cache (#16941)

Woosuk Kwon committed over 1 year ago

[Model] Use autoweightloader for mamba (#16950)

Flora Feng committed over 1 year ago

[Bugfix] Fix the issue where llm.generate cannot be called repeatedly after setting GuidedDecodingParams (#16767)

Chauncey committed over 1 year ago

[Perf] Optimize `_update_states` for GPU model runner (#16910)

SnowCharm committed over 1 year ago

[Doc] Update ai_accelerator/hpu-gaudi.inc.md (#16956)

Michael Yao committed over 1 year ago

[Bugfix] Fix f-string for Python 3.9-3.11 (#16962)

Cyrus Leung committed over 1 year ago