Phase 1: Run full pipeline to populate KV caches with real model weights.
Phase 2: For each layer, gather KV in mixed FP8/BF16 format, run both
production FMHA and PyTorch SDPA, compare cosine similarity.
Uses random Q (not model-generated) to isolate FMHA kernel accuracy
from upstream pipeline issues.
Test loads real model weights, runs attention forward for layers 0-4,
compares production B1 mixed FP8 FMHA output vs PyTorch SDPA reference.
This will reveal the FMHA cosine degradation (was 0.679 at L1) with
real data patterns, not just synthetic random data.
Production values: HD=512, NOPE=448, ROPE=64, H=128, 8 GPUs.
