Ashwin Bharambe c1f7ba3aed Split safety into (llama-guard, prompt-guard, code-scanner) (#400) ... 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.)		2024-11-11 09:29:18 -08:00
..
__init__.py	Remove "routing_table" and "routing_key" concepts for the user (#201)	2024-10-10 10:24:13 -07:00
conftest.py	Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376)	2024-11-05 16:22:33 -08:00
fixtures.py	Split safety into (llama-guard, prompt-guard, code-scanner) (#400)	2024-11-11 09:29:18 -08:00
pasta.jpeg	Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376)	2024-11-05 16:22:33 -08:00
test_prompt_adapter.py	Added tests for persistence (#274)	2024-10-22 19:41:46 -07:00
test_text_inference.py	migrate model to Resource and new registration signature (#410)	2024-11-08 16:12:57 -08:00
test_vision_inference.py	remote::vllm now works with vision models	2024-11-06 16:07:17 -08:00
utils.py	Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376)	2024-11-05 16:22:33 -08:00