deephermes-3-mistral-24b-preview
best known per operation on the selected GPU
2 operations · 2 families · 64 eligible runs
0 of 2 operations have a usable best known on NVIDIA B200 · 2 without one
Best known on NVIDIA B200
Operation · workload
Best known
Record
Trust
Observed
other1 operation
Attention value projection with transposesuite of 16 casesRIAC as wellnot usable24.9µsReported · license unknown · no source2026-08-22
No entry in this cohort passes the usability policy (no public source, no install recipe, license unknown); the fastest known is shown. Measured by the source's own harness. Ranked by its metric under ranking-v1. 16 more entries in this cohort.
no sourcelicense unknownno install recipeCohort on the operation page →Run detail →
rope1 operation
Grouped query attention with RoPE backwardsuite of 16 casesRIAC as wellnot usable316.3µsReported · license unknown · no source2026-08-15
No entry in this cohort passes the usability policy (no public source, no install recipe, license unknown); the fastest known is shown. Measured by the source's own harness. Ranked by its metric under ranking-v1. 18 more entries in this cohort.
no sourcelicense unknownno install recipeCohort on the operation page →Run detail →
Coverage gaps on NVIDIA B200
Operation
Family
Status
other
measured · no usable entry (no public source, no install recipe, license unknown)
rope
measured · no usable entry (no public source, no install recipe, license unknown)
No eligible evidence yet for these operations. Challenges →
Sources: NVIDIA SOL-ExecBench (2026-08-24)How comparison worksJSON