forked from phoenix-oss/llama-stack-mirror
* Significantly simpler and malleable test setup * convert memory tests * refactor fixtures and add support for composable fixtures * Fix memory to use the newer fixture organization * Get agents tests working * Safety tests work * yet another refactor to make this more general now it accepts --inference-model, --safety-model options also * get multiple providers working for meta-reference (for inference + safety) * Add README.md --------- Co-authored-by: Ashwin Bharambe <ashwin@meta.com> |
||
|---|---|---|
| .. | ||
| bedrock | ||
| databricks | ||
| fireworks | ||
| ollama | ||
| sample | ||
| tgi | ||
| together | ||
| vllm | ||
| __init__.py | ||