phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

routers for inference chat_completion with models dependency

Browse source
This commit is contained in:
Xi Yan 2024-09-19 20:59:32 -07:00
parent 47be4c7222
commit d2ec822b12
5 changed files with 113 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

29
llama_stack/distribution/utils/dynamic.py
View file

@ -38,19 +38,24 @@ async def instantiate_provider(
elif isinstance(provider_spec, RouterProviderSpec):
method = "get_router_impl"
assert isinstance(provider_config, list)
inner_specs = {x.provider_id: x for x in provider_spec.inner_specs}
inner_impls = []
for routing_entry in provider_config:
impl = await instantiate_provider(
inner_specs[routing_entry.provider_id],
deps,
routing_entry,
)
inner_impls.append((routing_entry.routing_key, impl))
if isinstance(provider_config, list):
inner_specs = {x.provider_id: x for x in provider_spec.inner_specs}
inner_impls = []
for routing_entry in provider_config:
impl = await instantiate_provider(
inner_specs[routing_entry.provider_id],
deps,
routing_entry,
)
inner_impls.append((routing_entry.routing_key, impl))
config = None
args = [inner_impls, deps]
config = None
args = [inner_impls, deps]
elif isinstance(provider_config, str) and provider_config == "models-router":
config = None
args = [[], deps]
else:
raise ValueError(f"provider_config {provider_config} is not valid")
else:
method = "get_provider_impl"