Attention score value matmul
Fused attention score-value matrix multiplication that computes attention_weights @ V followed by transpose and reshape. This is the second major matmul in attention (after QK^T softmax) and appears in every self-attention and cross-attention layer throughout SDXL UNet.
Reported evidence · last observed 2026-08-18. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 16 cases · mean latencyhead_dim = 64 · num_heads = 20 · hidden_size = 128016 cases
Not measured on H100 for this workload. Challenges →
113.1µs77% SOL1.00×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
215.0µs73% SOL1.14×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
315.2µs73% SOL1.15×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
415.3µs73% SOL1.17×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
515.4µs73% SOL1.17×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
615.4µs73% SOL1.18×Reported · license unknown · no source2026-07-16
Measured exactly what you asked. Reported by source; not independently reproduced.
715.5µs73% SOL1.18×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
815.5µs73% SOL1.18×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
915.7µs72% SOL1.19×Reported · license unknown · no source2026-08-07
Measured exactly what you asked. Reported by source; not independently reproduced.
1016.7µs71% SOL1.27×Reported · license unknown · no source2026-07-11
Measured exactly what you asked. Reported by source; not independently reproduced.
1117.0µs71% SOL1.30×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
1217.7µs69% SOL1.35×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
1329.6µs55% SOL2.25×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.