Cerebras
Configure Cerebras Inference with Continue for fast model inference using specialized silicon, including setup instructions for Llama 3.1 70B model
Cerebras Inference uses specialized silicon to provides fast inference.
- Create an account in the portal here.
- Create and copy the API key for use in Continue.
- Update your Continue config file:
name: My Config
version: 0.0.1
schema: v1
models:
- name: Cerebras Llama 3.1 70B
provider: cerebras
model: llama3.1-70b
apiKey: <YOUR_CEREBRAS_API_KEY>