phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 13:32:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updates

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-16 17:12:09 -07:00
parent ea9664874d
commit af7472cdb0
26 changed files with 293 additions and 185 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/distributions/meta-reference-gpu/run.yaml
View file

@ -84,15 +84,25 @@ providers:
provider_type: inline::rag-runtime
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
metadata_store:
type: kv_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
inference_store:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
conversations_store:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/conversations.db
storage:
backends:
default_kv_store:
type: kv_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
default_sql_store:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
metadata:
namespace: registry
backend: default_kv_store
inference:
table_name: inference_store
backend: default_sql_store
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: default_sql_store
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}