phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

mvp

Browse source
This commit is contained in:
Xi Yan 2024-10-04 00:25:57 -07:00
parent 4f07aca309
commit 3cbe3a72e8
10 changed files with 230 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

18
tests/examples/local-run.yaml
View file

@ -36,14 +36,18 @@ api_providers:
config: {}
routing_table:
inference:
- provider_type: meta-reference
# - provider_type: meta-reference
# config:
# model: Llama3.2-1B-Instruct
# quantization: null
# torch_seed: null
# max_seq_len: 4096
# max_batch_size: 1
# routing_key: Llama3.2-1B-Instruct
- provider_type: remote::tgi
config:
model: Llama3.2-1B
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
routing_key: Llama3.2-1B
url: http://127.0.0.1:5009
routing_key: Llama3.1-8B-Instruct
safety:
- provider_type: meta-reference
config: