will brown
will brown
Would be nice to have batch inference support similar to [`mlx_parallm`](https://github.com/willccbb/mlx_parallm), happy to try and add soon. @Blaizzy can you assign this to me?
## Description ## Type of Change - [ ] Bug fix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [ ]...
requested features: * "interleaved thinking" * citations
## Description WIP Pattern to allow intercepting requests from OpenAI-compatible CLI agent running inside sandbox by proxying OpenAI base url ## Type of Change - [ ] Bug fix (non-breaking...
## Summary - add a configurable SandboxEnv wrapper for Terminal-Bench tasks that stages assets in a fresh sandbox and runs the official tests during post-rollout - cache the test outcome...