Skip to content
KernelIndex
Search⌘K

GEMM n4096 k5376

0 eligible runs
gemm

General matrix multiply (GEMM) C = A @ B.T. Captured from Gemma 3 27B q_proj (hidden=5376, q_heads=32, head_dim=128 → N=4096).

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 = 5376
mvariable
nconstant = 4096
determinismunspecified
constraintsNo mutation or aliasing
Identity
aliasgemm_n4096_k5376modelgemma-3-27bsha256920f3da6320d…
No source imports for this operation yet.How records are decidedJSON