pub static ATTN_PHASE_US: [AtomicU64; 4]Expand description
Per-phase host-time accumulators for the prefill ATTENTION path
(ATLAS_PREFILL_HOST_TIMING=1). Index: 0=qkv projections, 1=everything
between qkv and the attention call (deinterleave + per-head norms + RoPE +
KV write), 2=the attention kernel call itself, 3=o_proj + head gate.
Summed across layers; read and reset once per prefill.