GQA paged prefill causal h32 kv8 d128 ps1
Batched Grouped Query Attention prefill with a paged KV cache. Causal mask is applied. Captured from Llama-3.1-8B during incremental prefill.
Reported evidence · last observed 2026-08-21. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 38 cases · mean latency76 cases
Not measured on H100 for this workload. Challenges →
15.11µs99% SOL1.00×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
25.11µs99% SOL1.00×Reported · license unknown · no source2026-08-09
Measured exactly what you asked. Reported by source; not independently reproduced.
35.18µs99% SOL1.01×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
45.63µs99% SOL1.10×Reported · license unknown · no source2026-08-05
Measured exactly what you asked. Reported by source; not independently reproduced.
56.46µs99% SOL1.27×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
66.97µs99% SOL1.37×Reported · license unknown · no source2026-07-16
Measured exactly what you asked. Reported by source; not independently reproduced.
78.96µs98% SOL1.76×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
810.7µs98% SOL2.09×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
911.1µs98% SOL2.16×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
1011.1µs98% SOL2.18×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
1111.3µs98% SOL2.21×Reported · license unknown · no source2026-07-18
Measured exactly what you asked. Reported by source; not independently reproduced.
1211.4µs97% SOL2.23×Reported · license unknown · no source2026-08-04
Measured exactly what you asked. Reported by source; not independently reproduced.
1311.5µs97% SOL2.25×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
1411.6µs98% SOL2.28×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
1512.2µs97% SOL2.39×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
1612.3µs97% SOL2.41×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
1712.4µs97% SOL2.42×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
1812.4µs97% SOL2.43×Reported · license unknown · no source2026-07-29
Measured exactly what you asked. Reported by source; not independently reproduced.
1912.8µs97% SOL2.50×Reported · license unknown · no source2026-08-03
Measured exactly what you asked. Reported by source; not independently reproduced.
2013.4µs97% SOL2.62×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
2113.4µs97% SOL2.63×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
2213.8µs97% SOL2.70×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
2314.0µs97% SOL2.75×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
2414.4µs97% SOL2.82×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
2515.7µs97% SOL3.07×Reported · license unknown · no source2026-07-15
Measured exactly what you asked. Reported by source; not independently reproduced.
2616.0µs96% SOL3.14×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
2719.1µs95% SOL3.74×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
2819.5µs96% SOL3.81×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
2933.6µs90% SOL6.59×Reported · license unknown · no source2026-08-12
Measured exactly what you asked. Reported by source; not independently reproduced.
3040.9µs92% SOL8.01×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
Implementations
Show all 50 implementations ›Showing all 50 implementations ⌄
Semantics
Also indexed as 015-gqa-paged-prefill-causal-h32-kv8-d128-ps1 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.