phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 09:44:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: OAI compat endpoint for meta reference inference provider

Browse source
This commit is contained in:
Eric Huang 2025-04-17 11:10:09 -07:00 • committed by Eric Huang
parent 8bd6665775
commit c171fc6062
8 changed files with 1184 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/verifications/conf/meta_reference.yaml Normal file
View file

@ -0,0 +1,8 @@
# 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: {}