phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 21:20:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-07 11:57:20 -07:00
parent 63cf5dda50
commit b239c57c54
8 changed files with 25 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -20,7 +20,7 @@ providers:
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
quantization:
type: ${env.QUANTIZATION_TYPE:bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:null}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -32,7 +32,7 @@ providers:
checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:null}
quantization:
type: ${env.QUANTIZATION_TYPE:bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:null}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
vector_io:
- provider_id: faiss
provider_type: inline::faiss

2
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -20,7 +20,7 @@ providers:
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
quantization:
type: ${env.QUANTIZATION_TYPE:bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:null}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}