phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 01:17:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-12 21:44:03 -08:00
parent 8efe33646d
commit de44af1501
9 changed files with 153 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

12
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}
max_seq_len: 4096
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
memory:
@ -72,11 +72,11 @@ metadata_store:
namespace: null
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
models: []
# - metadata: {}
# model_id: ${env.INFERENCE_MODEL}
# provider_id: meta-reference-inference
# provider_model_id: null
shields: []
memory_banks: []
datasets: []