For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

enqueue_matmul_kernel_naive

def enqueue_matmul_kernel_naive[EpilogueFnType: ElementwiseEpilogueFn, //, *, transpose_b: Bool, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None], has_epilogue_fn: Bool](c: TileTensor[Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type], a: TileTensor[Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b: TileTensor[Engine=b.Engine, address_space=b.address_space, linear_idx_type=b.linear_idx_type], epilogue_fn: EpilogueFnType, ctx: DeviceContext)

Enqueues matmul_kernel_naive, storing through epilogue_fn when has_epilogue_fn is set.

Parameters:

• ​EpilogueFnType (ElementwiseEpilogueFn): Type of epilogue_fn (inferred).
• ​transpose_b (Bool): Whether b is stored as (N, K).
• ​elementwise_lambda_fn (Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None]): Legacy epilogue lambda.
• ​has_epilogue_fn (Bool): Whether epilogue_fn stores the output.

Args:

• ​c (TileTensor[Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type]): Rank-2 output tensor.
• ​a (TileTensor[Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type]): Rank-2 left operand.
• ​b (TileTensor[Engine=b.Engine, address_space=b.address_space, linear_idx_type=b.linear_idx_type]): Rank-2 right operand.
• ​epilogue_fn (EpilogueFnType): Value epilogue, used when has_epilogue_fn is set.
• ​ctx (DeviceContext): Device context for the launch.