Michael Chus 8d6eaef5de Update perf benchmark report methodology to reflect new design ...

Remove references to pre-benchmark power calibration and dcgmi
targeted_power. Document platform_power_score ramp-up methodology,
PowerSustainScore fallback to steady-state power, and full-budget
single-precision phases.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-16 00:31:58 +03:00

audit

Update perf benchmark report methodology to reflect new design

2026-04-16 00:31:58 +03:00

bible @ 1d89a4918e

Update bible submodule

2026-04-08 07:14:31 +03:00

bible-local

Split bee-bench into perf and power workflows

2026-04-14 17:33:13 +03:00

internal

chore: commit pending repo changes

2026-03-31 22:17:36 +03:00

iso

Tune bee-gpu-burn single-precision benchmark phases

2026-04-16 00:05:47 +03:00

scripts

Drop legacy non-container builders

2026-03-16 00:23:55 +03:00

.env.example

fix: run-builder.sh uses BUILDER_USER from .env, not hardcoded

2026-03-08 18:48:33 +03:00

.gitignore

Disable precision fallback and pin cuBLAS 13.1

2026-04-14 10:17:44 +03:00

.gitmodules

Embed Reanimator Chart web viewer

2026-03-15 22:07:42 +03:00

PLAN.md

Add NVIDIA stress loader selection and DCGM 4 support

2026-03-31 11:15:15 +03:00

Description

No description provided

71 MiB

Languages

Go 83.4%

Shell 12.8%

C 3.6%

Dockerfile 0.1%