[BugFix] Fix async scheduling + reasoning with struct output (#31332)

Nick Hill committed 11 months ago

[Hybrid] Mamba2 prefix cache blocks freeing for running requests (#28047)

Stan Wozniak committed 11 months ago

[Model][Ernie4.5-VL] Support video metadata for timestamp rendering (#31274)

SongHe committed 11 months ago

use the same stream for cuda graph catpure and replay for NCCL (#29207)

Amir Samani committed 11 months ago

[Doc] Add troubleshooting for Triton PTX error about undefined gpu-name (#31338)

Isotr0py committed 11 months ago

[Benchmark Suite] improve cpu Benchmark Suite tests and comparison report for 0.12.0 (#30994)

Louie Tsai committed 11 months ago

[Frontend] add FunctionGemma tool parser support (#31218)

Mark Gatere committed 11 months ago

[Doc] Add tool call parser documentation for GPT-OSS models (#31212)

Amith KK committed 11 months ago

[Bugfix] Fix eagle dp tests on A100 (#31241)

Richard Zou committed 11 months ago

[Perf] Add skip_clone to SamplingParams for internal request handling (#31041)

Michael Goin committed 11 months ago

[Chore][1/2] Drop `v0.14` deprecations (#31285)

Cyrus Leung committed 11 months ago

[Bugfix] Remove dead `block_quant_to_tensor_quant` function (#31294)

ゆり committed 11 months ago

[cli] complete vllm cli help message (#31226)

Ning Xie committed 11 months ago

[Bugfix][Hardware][AMD] Fix FP8 dtype in silu_mul quantization (#31179)

Kevin McKay committed 11 months ago

[CI] Reorganization pooling_mteb_test (#31265)

wang.yuqi committed 11 months ago

[PERF] Add interleaved memory allocation to NUMA module (#30800)

skaraban3807 committed 11 months ago

[Chore] Bump `lm-eval` version (#31264)

Cyrus Leung committed 11 months ago

[Chore] Remove unused `noqa`s (#31263)

Cyrus Leung committed 11 months ago

[Bugfix] Fix `max_model_len="auto"` handling (#31260)

Cyrus Leung committed 11 months ago

[Model] Introduce verify_and_update_model_config for VerifyAndUpdateConfig. (#31131)

wang.yuqi committed 11 months ago