GEMM n5376 k4096
0 eligible runs
gemm
General matrix multiply (GEMM) C = A @ B.T. Captured from Gemma 3 27B o_proj (q_heads*head_dim=4096 → hidden=5376).
Current records
No published measurement for the selected workload.
Implementations
Implementation
Runtime
Best latency
Evidence
Availability
Semantics
Inputs and outputs
afp16 [m, k]
bfp16 [n, k]
cfp16 [m, n]
Axes and behavior
kconstant = 4096
mvariable
nconstant = 5376
determinismunspecified
constraintsNo mutation or aliasing
Identity
No source imports for this operation yet.How records are decidedJSON