Mojo function
batched_matmul_dynamic_scaled_fp8_naive
batched_matmul_dynamic_scaled_fp8_naive[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, scales_granularity_mnk: IndexList[3], transpose_b: Bool = False](c_device: NDBuffer[c_type, 3, origin, shape], a_device: NDBuffer[a_type, 3, origin, shape], b_device: NDBuffer[b_type, 3, origin, shape], a_scales_device: NDBuffer[a_scales_type, 3, origin, shape], b_scales_device: NDBuffer[b_scales_type, 3, origin, shape], ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!