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
Add a CodeTriage badge to vllm
Help out
- Issues
- [Rust Frontend] Add Rust Apertus tool parser
- [Bugfix][Realtime] Add idle watchdog for audio WebSocket sessions
- [Bug]: /v1/realtime audio sessions can retain KV cache indefinitely when clients stay connected without final=True
- [BugFix] Fix decode-phase blocks not stored in CPU KV cache offloading
- [Core] Add post-load weight processing registry
- [Bugfix][Core] Fix request-bound KV cache sizing
- [Bug]: Llama-4-Scout-FP8 tool calls left in content (not parsed into tool_calls) — pythonic parser vs JSON output mismatch, breaks Claude Code
- [XPU] Low-latency all-to-all Expert-Parallellism backend for batched MoE
- Title: [BugFix] Rebuild InputBatch when max_model_len is auto-reduced
- [WideEP] Remove DeepEP high-throughput backend, redirect to DeepEP v2
- Docs
- Python not yet supported