[V1] Override `mm_counts` for dummy data creation (#15703)

Cyrus Leung committed over 1 year ago

fix test_phi3v (#15321)

pansicheng committed over 1 year ago

[doc] update conda to usage link in installation (#15761)

Reid committed over 1 year ago

[Bugfix] Fix Mistral guided generation using xgrammar (#15704)

Julien Denize committed over 1 year ago

[CI] xgrammar structured output supports Enum. (#15757)

Chauncey committed over 1 year ago

[Bugfix] Fix Mllama interleaved images input support (#15564)

Isotr0py committed over 1 year ago

[V1][Minor] Simplify rejection sampler's parse_output (#15741)

Woosuk Kwon committed over 1 year ago

[V1] Support interleaved modality items (#15605)

Roger Wang committed over 1 year ago

[Feature][Disaggregated] Support XpYd disaggregated prefill with MooncakeStore (#12957)

shangmingc committed over 1 year ago

[V1] [Feature] Collective RPC (#15444)

wwl2755 committed over 1 year ago

[FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433)

TJian committed over 1 year ago

[doc] update doc (#15740)

Reid committed over 1 year ago

[Kernel][TPU][ragged-paged-attn] vLLM code change for PR#8896 (#15659)

yarongmu-google committed over 1 year ago

[TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714)

Nicolò Lucchesi committed over 1 year ago

[Bugfix] set VLLM_WORKER_MULTIPROC_METHOD=spawn for vllm.entrypoionts.openai.api_server (#15700)

Jinzhen Lin committed over 1 year ago

Use numba 0.61 for python 3.10+ to support numpy>=2 (#15692)

cyyever committed over 1 year ago

[CI] Speed up V1 structured output tests (#15718)

Russell Bryant committed over 1 year ago

[Bugfix] LoRA V1: add and fix entrypoints tests (#15715)

Varun Sundar Rabindranath committed over 1 year ago

[Misc][V1] Misc code streamlining (#15723)

Nick Hill committed over 1 year ago

[Docs] Document v0 engine support in reasoning outputs (#15739)

Ce Gao committed over 1 year ago