[DP] Fix Prometheus Logging (#21257)

Robert Shaw committed over 1 year ago

[Attention] Clean up iRoPE in V1 (#21188)

Lucas Wilkinson committed over 1 year ago

[Misc] Add dummy maverick test (#21199)

Ming Yang committed over 1 year ago

[BugFix] make utils.current_stream thread-safety (#21252) (#21253)

simpx committed over 1 year ago

[CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)

Li, Jiang committed over 1 year ago

[Misc] Add sliding window to flashinfer test (#21282)

Woosuk Kwon committed over 1 year ago

Add Nvidia ModelOpt config adaptation (#19815)

Zhiyu committed over 1 year ago

[Misc] unify variable for LLM instance (#20996)

Ning Xie committed over 1 year ago

[Docs] Make tables more space efficient in `supported_models.md` (#21291)

Harry Mellor committed over 1 year ago

[Docs] Fix hardcoded links in docs (#21287)

Harry Mellor committed over 1 year ago

[Model][1/N] Support multiple poolers at model level (#21227)

Cyrus Leung committed over 1 year ago

[Bugfix] Fix missing placeholder in logger debug (#21280)

Cyrus Leung committed over 1 year ago

Add the instruction to run e2e validation manually before release (#21023)

Huy Do committed over 1 year ago

[Docs] Add RFC Meeting to Issue Template (#21279)

Simon Mo committed over 1 year ago

[CI] Cleanup modelscope version constraint in Dockerfile (#21243)

Kay Yan committed over 1 year ago

[bugfix] fix syntax warning caused by backslash (#21251)

Jiayi Yan committed over 1 year ago

[Model] Support VLMs with transformers backend (#20543)

Raushan Turganbay committed over 1 year ago

[Model] use AutoWeightsLoader for bart (#18299)

Calvin Chen committed over 1 year ago

Enable v1 metrics tests (#20953)

Seiji Eicher committed over 1 year ago

[TPU] support fp8 kv cache quantization (#19292)

Chengji Yao committed over 1 year ago