[Feature] Add `vllm bench` CLI (#13993)

Randy Chen committed over 1 year ago

[release] Add commands to clean up logs on TPU release node (#14642)

Kevin H. Luu committed over 1 year ago

[Bugfix][V1][PP] Only warmup sampler at last PP rank (#14643)

Cody Yu committed over 1 year ago

[V1][TPU] Pad the block_table.shape[1] so the ragged paged attention can handle correctly (#14597)

iefgnoix committed over 1 year ago

Fix run_tpu_test (#14641)

Richard Liu committed over 1 year ago

[V1] Delay all xgrammar usage until needed (#14616)

Russell Bryant committed over 1 year ago

fix some typos : supported_head_sizes (#14627)

Yang.Tao committed over 1 year ago

[V1] Remove cache from StructuredOutputManager (#14622)

Russell Bryant committed over 1 year ago

[Hardware][Intel GPU] upgrade IPEX dependency to 2.6.10. (#14564)

Kunshang Ji committed over 1 year ago

[BugFix/Build] Fix sparse kernels not getting built on hopper (#14572)

Lucas Wilkinson committed over 1 year ago

docs: Add documentation for s390x cpu implementation (#14198)

Dilip Gowda Bhagavan committed over 1 year ago

[V1] Add regex structured output support with xgrammar (#14590)

Russell Bryant committed over 1 year ago

Uninstall dependencies before installing requirements/tpu.txt (#14586)

Richard Liu committed over 1 year ago

[Bugfix] Update `--hf-overrides` for `Alibaba-NLP/gte-Qwen2` (#14609)

Cyrus Leung committed over 1 year ago

dynamic distpatch of fp8 kernels (#14245)

Jeff Daily committed over 1 year ago

benchmarks: simplify test jsonschema (#14567)

Russell Bryant committed over 1 year ago

[VLM] Cleanup siglip legacy code and fix broken paligemma multimodal processor (#14602)

Isotr0py committed over 1 year ago

[Perf]:Optimize qwen2-vl to reduce cudaMemcpyAsync (#14377)

yexin(叶鑫) committed over 1 year ago

[Misc] Correct deepseek-vl2 chat template (#14558)

Isotr0py committed over 1 year ago

[V1][Core] Fix memory issue with logits & sampling (#14508)

Roger Wang committed over 1 year ago