[Structured Outputs][V1] Skipping with models doesn't contain tokenizers (#20365)

Aaron Pham committed over 1 year ago

[Misc] small update (#20462)

Reid committed over 1 year ago

Add ignore consolidated file in mistral example code (#20420)

汪志鹏 committed over 1 year ago

[Platform] Add custom default max tokens (#18557)

Gabriel Marinho committed over 1 year ago

[Misc] Change warn_for_unimplemented_methods to debug (#20455)

Michael Goin committed over 1 year ago

[Bugfix] Register reducer even if transformers_modules not available (#19510)

Seiji Eicher committed over 1 year ago

[Misc] Fix `Unable to detect current VLLM config. Defaulting to NHD kv cache layout` warning (#20400)

Nicolò Lucchesi committed over 1 year ago

[Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864)

bnellnm committed over 1 year ago

[Misc] Remove _maybe_ignore_quant_config from GLM4.1v (#20432)

Yuxuan Zhang committed over 1 year ago

[Misc] adjust for ipv6 for mookcacke url parse (#20107)

Ning Xie committed over 1 year ago

[Misc] Clean up InternVL family config registration (#19992)

Isotr0py committed over 1 year ago

[CI] Trimming some failing test groups from AMDPRODUCTION. (#20390)

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

[Frontend] fix duplicate output for bench subcmd (#20446)

Reid committed over 1 year ago

[Bugfix] Fix flaky `test_streaming_response` test (#20363)

Nicolò Lucchesi committed over 1 year ago

[Frontend] improve vllm bench <bench_type> --help display (#20430)

Reid committed over 1 year ago

[Misc] Automatically tag PRs to add new models (#20222)

Isotr0py committed over 1 year ago

[Model][2/N] Automatic conversion of CrossEncoding model (#19978)

wang.yuqi committed over 1 year ago

[Quantization] Bump to use latest bitsandbytes (#20424)

Jee Jee Li committed over 1 year ago

[CI/Build][CPU] Enable cross compilation in CPU release pipeline (#20423)

Li, Jiang committed over 1 year ago

[Kernel] refactor cpu worker v0 cache dtype (#20080)

Ning Xie committed over 1 year ago