forked from phoenix-oss/llama-stack-mirror
c1f7ba3aed
Splits the meta-reference safety implementation into three distinct providers: - inline::llama-guard - inline::prompt-guard - inline::code-scanner Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/ (Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.) |
||
|---|---|---|
| .. | ||
| bedrock | ||
| databricks | ||
| fireworks | ||
| hf-endpoint | ||
| hf-serverless | ||
| inline-vllm | ||
| meta-reference-gpu | ||
| meta-reference-quantized-gpu | ||
| ollama | ||
| remote-vllm | ||
| tgi | ||
| together | ||