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

Mojo function

dispatch_gemv

def dispatch_gemv[c_type: DType, a_type: DType, b_type: DType, //, transpose_b: Bool = False, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None] = None, elementwise_lambda_wrapper: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None] = None, elementwise_compute_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> SIMD[dtype, width]] = None, pdl_level: PDLLevel = PDLLevel()](c: TileTensor[c_type, Storage=c.Storage, address_space=c.address_space, linear_idx_type=c.linear_idx_type], a: TileTensor[a_type, Storage=a.Storage, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b: TileTensor[b_type, Storage=b.Storage, address_space=b.address_space, linear_idx_type=b.linear_idx_type], ctx: DeviceContext)

Dispatch M=1 (or N=1) matmul to GEMV or SM100 GEMM based on (N, K).

For most M=1 shapes GEMV is preferred, but for certain large (N, K) combinations the SM100 GEMM kernel achieves higher throughput. Add new (N, K) pairs to SM100_GEMV_SHAPES as they are identified through benchmarking.

N=1 always routes to GEMV: SM100 TMA requires N * sizeof(c_type) % 16 == 0.

Parameters:

c_type (DType): Output element type (inferred).
a_type (DType): Element type of the LHS operand a (inferred).
b_type (DType): Element type of the RHS operand b (inferred).
transpose_b (Bool): Whether b is stored transposed (defaults to False).
elementwise_lambda_fn (Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None]): Optional epilogue applied to each output element, passed to the SM100 GEMM path (defaults to None).
elementwise_lambda_wrapper (Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None]): Optional epilogue lambda passed to the GEMV path, folding in the compute lambda (defaults to None).
elementwise_compute_lambda_fn (Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> SIMD[dtype, width]]): Optional compute epilogue lambda, for example a static scale, passed to the SM100 GEMM path (defaults to None).
pdl_level (PDLLevel): Programmatic dependent launch level for the dispatched kernel (defaults to PDLLevel()).