phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Enable remote::vllm (#384)

Browse source 
* Enable remote::vllm

* Kill the giant list of hard coded models
This commit is contained in:
Ashwin Bharambe 2024-11-06 14:42:44 -08:00 • committed by GitHub
parent 093c9f1987
commit b10e9f46bb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 80 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/providers/registry/inference.py
View file

@ -61,15 +61,15 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.adapters.inference.ollama",
),
),
# remote_provider_spec(
# api=Api.inference,
# adapter=AdapterSpec(
# adapter_type="vllm",
# pip_packages=["openai"],
# module="llama_stack.providers.adapters.inference.vllm",
# config_class="llama_stack.providers.adapters.inference.vllm.VLLMImplConfig",
# ),
# ),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="vllm",
pip_packages=["openai"],
module="llama_stack.providers.adapters.inference.vllm",
config_class="llama_stack.providers.adapters.inference.vllm.VLLMInferenceAdapterConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(