forked from phoenix-oss/llama-stack-mirror
e2b5456e48
Add Runpod as a inference provider for openAI compatible managed endpoints. Testing - Configured llama stack from scratch, set `remote::runpod` as a inference provider. - Added Runpod Endpoint URL and API key. - Started llama-stack server - llama stack run my-local-stack --port 3000 ``` curl http://localhost:5000/inference/chat_completion \ -H "Content-Type: application/json" \ -d '{ "model": "Llama3.1-8B-Instruct", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Write me a 2 sentence poem about the moon"} ], "sampling_params": {"temperature": 0.7, "seed": 42, "max_tokens": 512} }' ``` --------- Signed-off-by: pandyamarut <pandyamarut@gmail.com>
9 lines
238 B
YAML
9 lines
238 B
YAML
name: runpod
|
|
distribution_spec:
|
|
description: Use Runpod for running LLM inference
|
|
providers:
|
|
inference: remote::runpod
|
|
memory: meta-reference
|
|
safety: meta-reference
|
|
agents: meta-reference
|
|
telemetry: meta-reference
|