strata serve: prompt 94 tokens = 0 reused + 94 read in 2000 ms (47.0 tok/s), 256 generated in 5335 ms (48.0 tok/s), drafts accepted 160 of 224, 1 checkpoints
strata serve: decode expert cache hit rate: 86.7% (122051 hits / 140725 lookups)
strata serve: KV streaming: 99.52% of 221760 block reads hit VRAM, 4.3 MiB read from RAM
