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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: RuntimeError: failed to map GGUF parameters (18288)
- [Bug]: Bench Serve encounter utf-8 UnicodeDecodeError
- [Bug]: NVFP4 MoE produces garbage output on SM120 (RTX 5080) with CPU offloading — Nemotron-Cascade-2-30B-A3B
- [Misc] Fix typos in test comments
- [Misc] Fix typos in source code comments
- [Proposal] Topology-Aware KV Cache Compression for Memory-Efficient Inference
- [RFC]: Add `max_tokens_per_doc` support for rerank and scoring endpoints
- [2/N] Pass `model_config` to the Attention constructors
- [Usage]: How to launch the Qwen3.5 service using vLLM on a V100 GPU
- [Core][Metrics] Remove `vllm:prompt_tokens_recomputed` metric
- Docs
- Python not yet supported