Skip to content
KernelIndex
Search⌘K

GEMM n57344 k8192

0 eligible runs
gemm

General matrix multiply (GEMM) C = A @ B.T. Captured from Llama 3.1/3.3 70B mlp.gate_up_proj (fused gate+up: 2 * intermediate=2 * 28672 = 57344).

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 = 8192
mvariable
nconstant = 57344
determinismunspecified
constraintsNo mutation or aliasing
Identity
aliasgemm_n57344_k8192modelllama-3-1-70bsha25684f9d6c3bf7d…
No source imports for this operation yet.How records are decidedJSON