[Model] Support Skywork-R1V (#15397)

pengyuange committed over 1 year ago

[ROCm][AMD][Build] Update AMD supported arch list (#15632)

Gregory Shtrasberg committed over 1 year ago

[Docs][V1] Optimize diagrams in prefix caching design (#15716)

simpx committed over 1 year ago

implement prometheus fast-api-instrumentor for http service metrics (#15657)

daniel-salib committed over 1 year ago

[Misc] cli auto show default value (#15582)

Reid committed over 1 year ago

[V1] TPU - Fix the chunked prompt bug (#15713)

Alexander Matveev committed over 1 year ago

[Bugfix] [torch.compile] Add Dynamo metrics context during compilation (#15639)

Luka Govedič committed over 1 year ago

[TPU] [Perf] Improve Memory Usage Estimation (#15671)

Robert Shaw committed over 1 year ago

[Misc] Remove stale func in KVTransferConfig (#14746)

shangmingc committed over 1 year ago

[Misc] Remove unused utils and clean up imports (#15708)

Cyrus Leung committed over 1 year ago

[Minor] Remove TGI launching script (#15646)

Woosuk Kwon committed over 1 year ago

Fix cpu offload testing for gptq/awq/ct (#15648)

Michael Goin committed over 1 year ago

[Bugfix] Fix regex compile display format (#15368)

Kebe committed over 1 year ago

[doc] add missing imports (#15699)

Reid committed over 1 year ago

[V1] Support disable_any_whtespace for guidance backend (#15584)

Russell Bryant committed over 1 year ago

[Bugfix] `embed_is_patch` for Idefics3 (#15696)

Cyrus Leung committed over 1 year ago

[Bugfix][v1] xgrammar structured output supports Enum. (#15594)

Chauncey committed over 1 year ago

[Model] Adding torch compile annotations to chatglm (#15624)

Jee Jee Li committed over 1 year ago

[Docs] Add "Generation quality changed" section to troubleshooting (#15701)

Harry Mellor committed over 1 year ago

[Frontend] update priority for --api-key and VLLM_API_KEY (#15588)

Reid committed over 1 year ago