phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 11:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-16 16:44:15 -08:00
parent de44af1501
commit 35b1a6f2dc
7 changed files with 54 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -16,7 +16,7 @@ providers:
- provider_id: meta-reference-inference
provider_type: inline::meta-reference
config:
# model: ${env.INFERENCE_MODEL}
model: ${env.INFERENCE_MODEL} # please make sure your inference model here is added as resource
max_seq_len: 4096
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
memory:
@ -73,10 +73,10 @@ metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
models: []
# - metadata: {}
# model_id: ${env.INFERENCE_MODEL}
# provider_id: meta-reference-inference
# provider_model_id: null
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: meta-reference-inference
provider_model_id: null
shields: []
memory_banks: []
datasets: []