mirror of
https://github.com/vllm-project/vllm.git
synced 2026-07-29 18:08:01 +00:00
89d3679221
Signed-off-by: DarkLight1337 <[email protected]> Signed-off-by: Harry Mellor <[email protected]> Co-authored-by: Harry Mellor <[email protected]>
445 B
445 B
Using vLLM
First, vLLM must be installed for your chosen device in either a Python or Docker environment.
Then, vLLM supports the following usage patterns:
- Inference and Serving: Run a single instance of a model.
- Deployment: Scale up model instances for production.
- Training: Train or fine-tune a model.