llama-stack
llama-stack copied to clipboard
feat: enable xpu support for meta-reference stack
trafficstars
This PR adds support of non-cuda XPU backend device into meta-reference stack path. Submitting as a draft PR to facilitate discussion around another patch in llama-models:
- https://github.com/meta-llama/llama-models/pull/233
Requires: https://github.com/meta-llama/llama-models/pull/233