mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-28 04:02:00 +00:00
8 lines
392 B
YAML
8 lines
392 B
YAML
# LLAMA_STACK_PORT=5002 llama stack run meta-reference-gpu --env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct --env INFERENCE_CHECKPOINT_DIR=<path_to_ckpt>
|
|
base_url: http://localhost:5002/v1/openai/v1
|
|
api_key_var: foo
|
|
models:
|
|
- meta-llama/Llama-4-Scout-17B-16E-Instruct
|
|
model_display_names:
|
|
meta-llama/Llama-4-Scout-17B-16E-Instruct: Llama-4-Scout-Instruct
|
|
test_exclusions: {}
|