vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][V1] Apply min-p in log-space to avoid a redundant softmax
- [Perf][V1] Reuse log-probs to avoid a second softmax in native sampler
- [Bugfix][Attention] Enable FlashInfer mm-prefix attention
- [Bugfix] Fix KV cache memory leak when all requests finish with connector
- [Bug]: test_mla_rope_kvcache_cat_fusion fails with FlashAttnMLA + fp8 KV cache (NotImplementedError)
- [XPU][UT] Fix test failure by using platform-aware imports
- [Bug]: test_tp_language_generation[Llama-3.2-1B-...parallel_setup{9,10}] times out (480s) on Hopper — server actually starts but exceeds the test deadline
- [Misc] Add remediation hints to MTP and PCP context-parallel errors
- [Rust Frontend] Add Jamba tool parser
- docs: add note on bitsandbytes batch size dependency
- Docs
- Python not yet supported