[BugFix] Add an env to disable moe chunking to work around compile incompatibility (#19642)

Ye (Charlotte) Qi committed over 1 year ago

[Chore] dedup logs (#19955)

Aaron Pham committed over 1 year ago

[Misc] Simplify vllm bench cli subcommand implementation (#19948)

Ye (Charlotte) Qi committed over 1 year ago

[Misc] Update model-specific PR tagging (#19949)

Roger Wang committed over 1 year ago

[doc] use snippets for contact us (#19944)

Reid committed over 1 year ago

[CI/Build] Auto tag perf benchmarks related PRs (#19943)

22quinn committed over 1 year ago

[Benchmark] fix request loss if "ping" is returned (#19535)

Wang, Yi committed over 1 year ago

[MISC] add cpu_kvcache_space_bytes to CacheConfig (#19812)

Ning Xie committed over 1 year ago

[Misc] add vllm_config in __init__ (#19866)

Ning Xie committed over 1 year ago

[Docs] Add GPT2ForSequenceClassification to supported models in docs (#19932)

Adrian committed over 1 year ago

[Multimodal] Optimize Qwen2/2.5-VL startup time (#19756)

Woosuk Kwon committed over 1 year ago

[doc] add contact us in community (#19922)

Reid committed over 1 year ago

[New model support]Support Tarsier2 (#19887)

汪志鹏 committed over 1 year ago

[Bugfix] Fix bnb 8bit model weights loading (#19917)

Isotr0py committed over 1 year ago

Fix: Check the type of params to be a Sequence not list. (#19910)

Rabin Adhikari committed over 1 year ago

[Misc] Clean up useless code (#19889)

wangxiyuan committed over 1 year ago

[Kernel] mark TorchSDPABackend swap_blocks NotImplementedError (#19749)

Ning Xie committed over 1 year ago

[CPU][CI] Fallback sliding window to v0 and fix CPU pooling model tests (#19901)

Li, Jiang committed over 1 year ago

Export NaNs in logits to scheduler_stats if output is corrupted (#18777)

Vlad Tiberiu Mihailescu committed over 1 year ago

[custom_op][vllm-plugin] update custom_op class to use op_registry (#19164)

Chendi.Xue committed over 1 year ago