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 supported6 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Failed to load modelopt quantized fp8 model
- [Bug]: xgrammar==0.17 not work when guided
- [Bug]: When using benchmark_serving with --metric-percentiles & --save-result, there is KeyError in save_to_pytorch_benchmark_format
- [Bug]: Fields not removed when save_detailed is not specified
- [Feature]: Freshly built docker image for GH200/ARM architeructre
- [Usage]: How can I get the result of each step of llm_engine.step()
- [Performance]: Why AWQ model‘s performance different from GPTQ model on A100&H100
- [RFC]: this object obtained from obj cache is not really used
- [Bug]: run on cpu: ModuleNotFoundError: No module named 'vllm.benchmarks'
- [Bug]: Failed to run an GPTQModel quantized model with vLLM
- Docs
- Python not yet supported