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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Drop the dangling NO_ATTENTION backend registration
- [Bugfix][LoRA] Whisper: opt the encoder into tower LoRA
- [Kernel] EFC-style epilogues for the CuTe DSL Lamport TP all-reduce
- [Perf] Batch sampling-mask transport and skip mask re-validation
- [Perf][Kernel][LoRA] Optimize Multi-LoRA kernels for fragmented token distributions
- [Bugfix][KV Offload] Preserve other writers temporary files on open failure
- [Bugfix][KVConnector] Split MLA kernel rows larger than the NIXL block into dense pages
- bench: add --metrics-url override for metrics scraping behind a router
- [Bugfix] Keep text after DeepSeek V3.1 tool calls
- [Bugfix][KV Connector] Mooncake: reject mismatched block sizes in the handshake
- Docs
- Python not yet supported