phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 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

11
llama_stack/providers/adapters/inference/vllm/__init__.py
View file

@ -4,12 +4,15 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from .config import VLLMImplConfig
from .vllm import VLLMInferenceAdapter
from .config import VLLMInferenceAdapterConfig
async def get_adapter_impl(config: VLLMImplConfig, _deps):
assert isinstance(config, VLLMImplConfig), f"Unexpected config type: {type(config)}"
async def get_adapter_impl(config: VLLMInferenceAdapterConfig, _deps):
from .vllm import VLLMInferenceAdapter
assert isinstance(
config, VLLMInferenceAdapterConfig
), f"Unexpected config type: {type(config)}"
impl = VLLMInferenceAdapter(config)
await impl.initialize()
return impl