Files
llama.cpp/scripts
LumpiastyandClaude Opus 5.5 62d442e7bf scripts: rx580-bench - decode at tg256 depth 4096, not tg32
The llama-bench sweep measured decode as tg32 at the default depth and the
README called it the continuity metric, while tg32 at n_ctx 32 is launch /
barrier bound on this card and is not a valid decode metric (it once read
-36% between builds at parity at tg256). lbsweep.sh now runs prefill
(-p $LB_P -n 0, depth 0) and decode (-p 0 -n 256 -d 4096, LB_N / LB_D) as
two invocations and labels depth cells (tg256@d4096). summarize.py marks
old depth-less tg rows as invalid-metric history. The README examples and
the reference values are updated to the 2026-10-24 production numbers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 00:33:22 +02:00
..
2026-09-07 21:10:06 +02:00
2026-03-08 12:30:21 +01:00
2025-08-18 22:06:44 +03:00
2026-10-15 16:20:14 +03:00
2025-08-18 22:06:44 +03:00
2026-09-07 21:10:06 +02:00
2026-09-12 16:09:46 +02:00