phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 12:21:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

router method wrapper

Browse source
This commit is contained in:
Xi Yan 2024-09-21 15:56:20 -07:00
parent 951cc9d7b7
commit 04f480d70c
2 changed files with 43 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/examples/router-table-run.yaml
View file

@ -20,14 +20,14 @@ provider_routing_table:
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
- routing_key: Meta-Llama3.1-8B
provider_id: meta-reference
config:
model: Meta-Llama3.1-8B
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
# - routing_key: Meta-Llama3.1-8B
# provider_id: meta-reference
# config:
# model: Meta-Llama3.1-8B
# quantization: null
# torch_seed: null
# max_seq_len: 4096
# max_batch_size: 1
# memory:
# - routing_key: keyvalue
# provider_id: remote::pgvector