randomllama commited on
Commit
d8b622a
·
verified ·
1 Parent(s): c56a4a1

sync: latest measured numbers

Browse files
Files changed (1) hide show
  1. LADDER.md +8 -0
LADDER.md CHANGED
@@ -133,3 +133,11 @@ Config FP8T8V = FP8T8b + `--enable-multimodal`. Results:
133
  **Production is now FP8T8V: fp8-KV + 8 concurrent streams + image input, one config.**
134
  Not yet measured: vision quality beyond the smoke probe, video input, vision+DFlash accept
135
  interaction, vision under concurrency. Treat image support as verified-working, not benchmarked.
 
 
 
 
 
 
 
 
 
133
  **Production is now FP8T8V: fp8-KV + 8 concurrent streams + image input, one config.**
134
  Not yet measured: vision quality beyond the smoke probe, video input, vision+DFlash accept
135
  interaction, vision under concurrency. Treat image support as verified-working, not benchmarked.
136
+
137
+ ## Pool expansion (2026-08-28 pm) — FP8T8X, production
138
+ FP8T8V + mem-fraction 0.90->0.92, single variable. KV pool 84,288 -> 244,032 tokens (2.9x;
139
+ the 262,144 ask minus page rounding), both target-fp8 and draft-bf16 pools. 8.9GB runtime
140
+ headroom kept. Gate PASS; c8 78.1 / c12 83.5 (curve unchanged); single-stream 27.0 code —
141
+ within the day's 27.0-29.3 noise band for this config family. Production = start-FP8T8X.sh:
142
+ fp8-KV + 8 streams + vision + 244k-token pool. Context-length raise beyond 131k = next rung
143
+ (needs rope/prefill verification, not just pool).