zeekay 1ccfab4d8f papers: kernel DSL migration + kernel-optimization catalog (incl. the flash-attention repetition bifurcation boundary) + cross-backend correctness finding ...

- hanzo-kernel-dsl: one-source #[kernel] DSL, 2 kernels drained to production, perf-gated migration
- hanzo-kernel-optimization: cross-backend kept-levers + dead-ends catalog + the flash-attn P*V
  bifurcation boundary (fusion & f32-P*V mutually exclusive on tensor cores -> eager is optimal)
- cross-backend-inference: the model-level correctness lesson (one numerically-vetted impl per op)

2026-07-03 19:04:20 -07:00

296 KiB

Raw History

View Raw