jgrusewski 6dd1aeca7e perf: disable replay buffer VRAM auto-sizing — cap at 500K entries ...

Auto-sizer inflated replay buffer to 15.8M entries on H100 (45% of 80GB VRAM).
The PER prefix scan inside the CUDA graph processes ALL 15.8M entries every step,
dominating step time. With buffer_size=500K, the scan processes 500K entries instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-19 09:20:15 +02:00

..

a100.toml

fix: restore explicit buffer_size in GPU profiles (auto-sizing removed)

2026-04-04 01:24:19 +02:00

default.toml

fix: restore explicit buffer_size in GPU profiles (auto-sizing removed)

2026-04-04 01:24:19 +02:00

h100.toml

perf: disable replay buffer VRAM auto-sizing — cap at 500K entries

2026-04-19 09:20:15 +02:00

rtx3050.toml

fix: restore explicit buffer_size in GPU profiles (auto-sizing removed)

2026-04-04 01:24:19 +02:00