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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Use server-generated keys for late-interaction query caches
- Confine connector cache files to shared storage
- Keep invalid structured-output requests from stopping the engine
- [Bug]: online FP8 (--quantization fp8) produces corrupted, non-EOS-terminating output on Qwen2.5-1.5B-Instruct
- [Bugfix][Spec Decode] Fix DSD K-lookup to count sampling-only requests, preventing K thrashing at batch boundaries
- [Bugfix][Rust Frontend] Avoid abort on empty prompt logprobs
- Add distributed LegoMem KV offload benchmark
- [Core] Report requests admitted while the scheduler is paused
- [Bugfix][DSv4] Skip zero-query-len prefill chunks in FlashMLA sparse prefill (complements #49059)
- [Model] Add tower and connector LoRA support for LFM2-VL
- Docs
- Python not yet supported