f9b3f00691
Previous run was grinding on CPU for 36+ minutes because the per-story V_i tensors were stored on CPU by the collector, and _subspace_concept_direction inherited that device. The per-concept eigh on 5120x5120 is glacial on CPU and fast on GPU (~1s). Add explicit device parameter; pass training device. Transfer result back to CPU for storage. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| amygdala_stories | ||
| amygdala_training | ||
| apollo_plugin | ||
| research | ||
| DESIGN.md | ||
| pyproject.toml | ||