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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: SLA-Tiered Scheduling for Latency/Throughput Optimization
- [Bug]: The find_matches function took 15 seconds to process 175 images in a single request.
- [Installation]: download wheel by commit:not found
- [Usage]: Is it possible to configure P2P kv-cache in multi-machine and multi-gpu scenarios?
- [Bug]: Qwen2.5-7B-Instruct fails to start with block_size=8 when TP=4
- [Bug]: vLLM (GPT-OSS) causes distorted tool argument names + infinite tool-call loop with Korean messenger tool
- [Feature]: Automatically infer Qwen3 reranker settings (remove need for hf_overrides)
- [Bug]: EAGLE3 failure with gpt-oss 20b and 120b
- [Bug]: Qwen3 Coder parser does not stream tool call arguments
- [Bug]: Ministral-3-14B-Instruct-2512 C++ Compilation Error with Torch Inductor and Batch Generation Failure with enforce_eager=False
- Docs
- Python not yet supported