strata serve: prompt 4022 tokens = 0 reused + 4022 read in 13599 ms (295.8 tok/s), 256 generated in 5866 ms (43.6 tok/s), drafts accepted 163 of 220, 1 checkpoints
strata serve: decode expert cache hit rate: 80.0% (104260 hits / 130369 lookups)
strata serve: KV streaming: 99.35% of 1971816 block reads hit VRAM, 51.3 MiB read from RAM
strata serve: suffix drafts: 2 windows, 5 of 6 drafts accepted
