diff --git a/PERFORMANCE_AUDIT.md b/PERFORMANCE_AUDIT.md index db964143..28e9b480 100644 --- a/PERFORMANCE_AUDIT.md +++ b/PERFORMANCE_AUDIT.md @@ -224,9 +224,9 @@ post-fusion structure. | **KV-1** | FP4 storage for CSA main compressed KV | M | Huge at long context | Next | ✅ Done | | **KV-2** | FP4 storage for HCA compressed KV | M | Same pattern as KV-1 | After KV-1 | ✅ Done | | **KV-3** | FP4 storage for indexer keys (pair with E7) | M | Throughput + paper compliance | After KV-2 |✅ Done | -| **P4** | RMSNorm fused into next quantize | S | 122 launches/token | After KV | -| **P5** | mHC pre_block + RMSNorm fused | S | ~120 launches/token | After P4 | -| **P6** | CUDA graph capture | L | **2–3× total** | After everything above | +| **P4** | RMSNorm fused into next quantize | S | 122 launches/token | ✅ Done | +| **P5** | mHC pre_block + RMSNorm fused | S | ~120 launches/token | ✅ Done (kernel, pending integration) | +| **P6** | CUDA graph capture | L | **2–3× total** | Next | ---