Skip to content
KernelIndex
Search⌘K

GEMM n3072 k6144

0 eligible runs
gemm

General matrix multiply (GEMM) C = A @ B.T. Captured from MiniMax M2 attn.o_proj (48*128=6144 -> 3072).

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 = 6144
mvariable
nconstant = 3072
determinismunspecified
constraintsNo mutation or aliasing
Identity
aliasgemm_n3072_k6144modelminimax-m2sha25652d675c93997…
No source imports for this operation yet.How records are decidedJSON