[Multimodal] Always enable hashing mm data (#23308)

Roger Wang committed about 1 year ago

[Bugfix] set system_message in phi4mini chat template (#23309)

jerryzhuang committed about 1 year ago

[V1] Remove unnecessary check for main thread (#23298)

Robert Shaw committed about 1 year ago

[Performance] V1 Pooling Models E2E Performance Optimization (#23162)

wang.yuqi committed about 1 year ago

[Doc] Fix batch-level DP example (#23325)

Cyrus Leung committed about 1 year ago

[Refactor] Simplify code for MM budget (#23310)

Cyrus Leung committed about 1 year ago

[Model] Add LFM2 architecture (#22845)

Paul Pak committed about 1 year ago

[BugFix] Fix Python 3.9 Support (#23306)

Jared O'Connell committed about 1 year ago

[Bugfix] Fix extra whitespace in strings caused by newline (#23272)

Cyrus Leung committed about 1 year ago

[Sampler] Support returning final logprobs (#22387)

22quinn committed about 1 year ago

[CI] Block the cu126 wheel build while broken (#23285)

Michael Goin committed about 1 year ago

[CI] Delete images older than 24h. (#23291)

QiliangCui committed about 1 year ago

[Model][VLM] Support R-4B Model (#23246)

杨奇(yann qi) committed about 1 year ago

[Compile] Fix Compile Warning SM100 Cutlass MLA (#23287)

Wentao Ye committed about 1 year ago

[V1][Mamba1] - Full CUDA and Piecewise CUDA Graphs Support (#23035)

Asaf Joseph Gardin committed about 1 year ago

[CI/Build] Split out mm processor tests (#23260)

Cyrus Leung committed about 1 year ago

[CPU] Refactor CPU W8A8 scaled_mm (#23071)

Li, Jiang committed about 1 year ago

[Optimization] Make new_block_ids None if empty (#23262)

Woosuk Kwon committed about 1 year ago

[CI Bugfix] Fix CI by fully removing --enable-prompt-adapter (#23284)

Michael Goin committed about 1 year ago

Remove duplicate entry in vllm.attention.__all__ (#23296)

Russell Bryant committed about 1 year ago