mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-05-06 09:38:33 -05:00
Folds in: bench/measure_peaks.py (real per-machine peak FLOPS + BW measurement), roofline.py reading from cache, manifest.py rejecting dirty trees on closed division, check_taxonomy.py --verify-against-sidecars flag, nanogpt_prefill emitting sidecars. Empirical findings: hardcoded M1 peaks were 5.5-7.7x off for this machine (M-series Pro/Max). The verify-against-sidecars flag caught a YAML claim that didn't survive real measurement (nanogpt-prefill dispatch claim was calibrated against wrong peaks). Branch parked. 6 of 10 iterations complete (counting 5.5).