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

merge

Browse source
This commit is contained in:
Xi Yan 2025-03-23 15:48:14 -07:00
commit a54d757ade
197 changed files with 9392 additions and 3089 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/templates/remote-vllm/vllm.py
View file

@ -43,7 +43,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="vllm-inference",
provider_type="remote::vllm",
config=VLLMInferenceAdapterConfig.sample_run_config(
url="${env.VLLM_URL}",
url="${env.VLLM_URL:http://localhost:8000/v1}",
),
)
embedding_provider = Provider(
@ -133,7 +133,7 @@ def get_distribution_template() -> DistributionTemplate:
},
run_config_env_vars={
"LLAMA_STACK_PORT": (
"5001",
"8321",
"Port for the Llama Stack distribution server",
),
"INFERENCE_MODEL": (