noonghunna 20ca297378 docs: refresh 4090 cross-rig knee with @laurimyllari's richer 38-cap sweep ...

His earlier 15-cap sweep (260-400W, 16832066) is superseded by a
38-cap sweep at 10W resolution from 230-600W (16854218) — strictly
richer envelope. Two findings worth surfacing:

- Firmware boost-clock plateau at SM 2610 MHz: caps 400-600W produce
  identical 51.96 TPS at 393W actual draw. Auto-plateau detector in
  power-cap-sweep.sh caught both sub-plateaus cleanly (400-470W and
  480-600W).
- decode-concurrent N=4 plateau lower than decode-single (46 vs 52
  TPS) — on a 4090 + 27B Q3_K_XL the GPU is under-load at c=4 even
  at full TDP, so single-stream wins. Useful cross-rig signal.

HARDWARE.md table + chart caption updated; chart regenerated with
both load-mode curves overlaid + plateau zone shaded.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-09 19:54:49 +00:00

232 KiB

1785x937px

Raw History