phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Further generalize Xi's changes (#88)

Browse source 
* Further generalize Xi's changes

- introduce a slightly more general notion of an AutoRouted provider
- the AutoRouted provider is associated with a RoutingTable provider
- e.g. inference -> models
- Introduced safety -> shields and memory -> memory_banks
  correspondences

* typo

* Basic build and run succeeded
This commit is contained in:
Ashwin Bharambe 2024-09-22 16:31:18 -07:00 • committed by GitHub
parent b8914bb56f
commit c1ab66f1e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 597 additions and 418 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/registry/inference.py
View file

@ -32,10 +32,6 @@ def available_providers() -> List[ProviderSpec]:
adapter_id="ollama",
pip_packages=["ollama"],
module="llama_stack.providers.adapters.inference.ollama",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
],
),
),
remote_provider_spec(
@ -56,11 +52,6 @@ def available_providers() -> List[ProviderSpec]:
],
module="llama_stack.providers.adapters.inference.fireworks",
config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
"Meta-Llama3.1-405B-Instruct",
],
),
),
remote_provider_spec(
@ -73,11 +64,6 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.adapters.inference.together",
config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
header_extractor_class="llama_stack.providers.adapters.inference.together.TogetherHeaderExtractor",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
"Meta-Llama3.1-405B-Instruct",
],
),
),
]