raise exception for pin_lora (#19809)

Ning Xie committed over 1 year ago

[Misc] [ROCm] Prevent surplus tensor reshape (#19803)

zsolt-borbely-htec committed over 1 year ago

[ROCm] [AITER] [Bugfix] Patch for AITER commit `648764942e552a8bb5fe16026703716a81f05374` (#18990)

TJian committed over 1 year ago

Mark invariant normalizer in Gemma as non-persistent (#19788)

Yu-Hang "Maxin" Tang committed over 1 year ago

[Bugfix] Add check_health to v1 async client. (#19821)

kourosh hakhamaneshi committed over 1 year ago

[Bugfix] Fix the linter (#19826)

Lu Fang committed over 1 year ago

Support embedding models in V1 (#16188)

Maximilien de Bayser committed over 1 year ago

[Quantization] Modify the logic of BNB double quantization (#19742)

Jee Jee Li committed over 1 year ago

[Misc][ROCm] Enforce no unused variable in ROCm C++ files (#19796)

Lu Fang committed over 1 year ago

Fix FA2 fallback for Blackwell V1 (#19781)

Michael Goin committed over 1 year ago

[Frontend] Expose custom args in OpenAI APIs (#16862)

afeldman-nm committed over 1 year ago

[BugFix] Fix use_cudagraph=False (#19612)

Richard Zou committed over 1 year ago

[Multimodal] Use fast processor for Qwen2/2.5-VL (#19789)

Woosuk Kwon committed over 1 year ago

[Core] More fixes to MultiModalEmbeddings type handling (#19715)

Russell Bryant committed over 1 year ago

[TPU] Update torch-xla version to include paged attention tuned block change (#19813)

QiliangCui committed over 1 year ago

[Core] Do not copy array during hashing (#19484)

Lukas Geiger committed over 1 year ago

Disable "Forbid direct 'import triton'" check for `vllm/triton_utils/importing.py` in an extensible way (#19783)

afeldman-nm committed over 1 year ago

docs: fix Slack bulletpoint in README (#19811)

Nathan Weinberg committed over 1 year ago

[v1] Support mamba2 (#19327)

Chen Zhang committed over 1 year ago

[Docs] Add Huzaifa Sidhpurwala to vuln mgmt team doc (#19808)

Russell Bryant committed over 1 year ago