diff --git a/llama_stack/distribution/templates/build_configs/local-vllm-build.yaml b/llama_stack/distribution/templates/build_configs/local-vllm-build.yaml index e907cb7c9..e333a137b 100644 --- a/llama_stack/distribution/templates/build_configs/local-vllm-build.yaml +++ b/llama_stack/distribution/templates/build_configs/local-vllm-build.yaml @@ -7,4 +7,4 @@ distribution_spec: safety: meta-reference agents: meta-reference telemetry: meta-reference -image_type: conda +image_type: conda \ No newline at end of file diff --git a/llama_stack/distribution/templates/remote-vllm-build.yaml b/llama_stack/distribution/templates/remote-vllm-build.yaml new file mode 100644 index 000000000..525c3a930 --- /dev/null +++ b/llama_stack/distribution/templates/remote-vllm-build.yaml @@ -0,0 +1,10 @@ +name: remote-vllm +distribution_spec: + description: Use remote vLLM for running LLM inference + providers: + inference: remote::vllm + memory: meta-reference + safety: meta-reference + agents: meta-reference + telemetry: meta-reference +image_type: docker \ No newline at end of file