Ashwin Bharambe 199f859eec feat(vllm): periodically refresh models (#2823) ... Just like #2805 but for vLLM. We also make VLLM_URL env variable optional (not required) -- if not specified, the provider silently sits idle and yells eventually if someone tries to call a completion on it. This is done so as to allow this provider to be present in the `starter` distribution. ## Test Plan Set up vLLM, copy the starter template and set `{ refresh_models: true, refresh_models_interval: 10 }` for the vllm provider and then run: ``` ENABLE_VLLM=vllm VLLM_URL=http://localhost:8000/v1 \ uv run llama stack run --image-type venv /tmp/starter.yaml ``` Verify that `llama-stack-client models list` brings up the model correctly from vLLM.		2025-07-18 15:53:09 -07:00
..
index.md	chore: kill inline::vllm (#2824)	2025-07-18 15:52:18 -07:00
inline_meta-reference.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
inline_sentence-transformers.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_anthropic.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_bedrock.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_cerebras-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_cerebras.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_databricks.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_fireworks-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_fireworks.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_gemini.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_groq-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_groq.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_hf_endpoint.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_hf_serverless.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_llama-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_nvidia.md	fix: allow default empty vars for conditionals (#2570)	2025-07-01 14:42:05 +02:00
remote_ollama.md	feat(ollama): periodically refresh models (#2805)	2025-07-18 12:20:36 -07:00
remote_openai.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_passthrough.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_runpod.md	feat: consolidate most distros into "starter" (#2516)	2025-07-04 15:58:03 +02:00
remote_sambanova-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_sambanova.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_tgi.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_together-openai-compat.md	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
remote_together.md	feat: consolidate most distros into "starter" (#2516)	2025-07-04 15:58:03 +02:00
remote_vllm.md	feat(vllm): periodically refresh models (#2823)	2025-07-18 15:53:09 -07:00
remote_watsonx.md	fix: allow default empty vars for conditionals (#2570)	2025-07-01 14:42:05 +02:00