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
- [CI][Bugfix] Fix triton import check error
- [RFC]: include past-reasoning for harmony(gpt-oss) formatting in chat completions API
- [Bug]: `strict` value in function definitions causes request error when using Mistral tokenizer
- [Feature][Hybrid] Integrate prefix caching into short conv models
- [RFC]: Fixing the inaccurate memory profiling
- [Usage]: How to recognize PDFs in DeepSeek-OCR with openai
- [Bug]: vllm serving deepseek-r1-0528 model on AWS EFA with 8*H200
- Use maximum number of batched tokens to autotune MoE
- [Bug]: Qwen3-VL-235B illegal memory access was encountered
- Adds Dockerfile arg for VLLM_PRECOMPILED_WHEEL_LOCATION
- Docs
- Python not yet supported