phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 11:42:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

wip

Browse source
This commit is contained in:
Xi Yan 2024-10-16 19:14:08 -07:00
parent c4d5d6bb91
commit 5eb53a7b77
15 changed files with 72 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

45
llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml
View file

@ -1,45 +0,0 @@
version: '2'
built_at: '2024-10-08T17:42:33.690666'
image_name: local-gpu
docker_image: local-gpu
conda_env: null
apis:
- memory
- inference
- agents
- shields
- safety
- models
- memory_banks
providers:
inference:
- provider_id: meta-reference
provider_type: meta-reference
config:
model: Llama3.1-8B-Instruct
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
safety:
- provider_id: meta-reference
provider_type: meta-reference
config:
llama_guard_shield: null
prompt_guard_shield: null
memory:
- provider_id: meta-reference
provider_type: meta-reference
config: {}
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}