mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-20 03:40:05 +00:00
68a2dfbad7
For self-hosted providers like Ollama (or vLLM), the backing server is running a set of models. That server should be treated as the source of truth and the Stack registry should just be a cache for those models. Of course, in production environments, you may not want this (because you know what model you are running statically) hence there's a config boolean to control this behavior. _This is part of a series of PRs aimed at removing the requirement of needing to set `INFERENCE_MODEL` env variables for running Llama Stack server._ ## Test Plan Copy and modify the starter.yaml template / config and enable `refresh_models: true, refresh_models_interval: 10` for the ollama provider. Then, run: ``` LLAMA_STACK_LOGGING=all=debug \ ENABLE_OLLAMA=ollama uv run llama stack run --image-type venv /tmp/starter.yaml ``` See a gargantuan amount of logs, but verify that the provider is periodically refreshing models. Stop and prune a model from ollama server, restart the server. Verify that the model goes away when I call `uv run llama-stack-client models list` |
||
|---|---|---|
| .. | ||
| index.md | ||
| inline_meta-reference.md | ||
| inline_sentence-transformers.md | ||
| inline_vllm.md | ||
| remote_anthropic.md | ||
| remote_bedrock.md | ||
| remote_cerebras-openai-compat.md | ||
| remote_cerebras.md | ||
| remote_databricks.md | ||
| remote_fireworks-openai-compat.md | ||
| remote_fireworks.md | ||
| remote_gemini.md | ||
| remote_groq-openai-compat.md | ||
| remote_groq.md | ||
| remote_hf_endpoint.md | ||
| remote_hf_serverless.md | ||
| remote_llama-openai-compat.md | ||
| remote_nvidia.md | ||
| remote_ollama.md | ||
| remote_openai.md | ||
| remote_passthrough.md | ||
| remote_runpod.md | ||
| remote_sambanova-openai-compat.md | ||
| remote_sambanova.md | ||
| remote_tgi.md | ||
| remote_together-openai-compat.md | ||
| remote_together.md | ||
| remote_vllm.md | ||
| remote_watsonx.md | ||