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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][Rust][Benchmark] Reuse allowed tokens in multi-turn generation
- [Bug]: gpt-oss chat completions return 500 when a prior tool call name contains special-token text
- [Bugfix][Frontend] Encode special-token text as plain text in gpt-oss legacy tool-call headers
- [Bugfix][SleepMode] Release CPU backups when discarding asleep allocations
- [Bug]: qwen3_coder: a repeated parameter breaks the streamed tool call arguments
- [Bugfix][Parser] Keep the first value of a repeated Qwen3 tool parameter
- [Frontend][Realtime] Add server-side turn detection (server_vad / semantic_vad) to /v1/realtime
- [Frontend] Stream diarized_json transcriptions as segment events
- [Frontend] Support output logprobs for gpt-oss in the Responses API (…
- [Bugfix][Frontend] Align DeepSeek V4.1 thinking precedence with Rust
- Docs
- Python not yet supported