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 struct
DistributedAllReduceAddRMSNormQuantFP8
struct DistributedAllReduceAddRMSNormQuantFP8
Implemented traits
AnyType,
ImplicitlyDestructible
Methods
execute
static def execute[dtype: DType, output_type: DType, scales_type: DType, rank: Int, target: StringSlice[StaticConstantOrigin], _trace_name: StringSlice[StaticConstantOrigin]](outputs: VariadicTensors[Output, static_specs=outputs.static_specs], outputs_scales: VariadicTensors[Output, static_specs=outputs_scales.static_specs], outputs_residual: VariadicTensors[Output, static_specs=outputs_residual.static_specs], inputs: VariadicTensors[Input, static_specs=inputs.static_specs], signal_buffers: VariadicTensors[MutableInput, static_specs=signal_buffers.static_specs], residuals: VariadicTensors[Input, static_specs=residuals.static_specs], gammas: VariadicTensors[Input, static_specs=gammas.static_specs], epsilons: VariadicTensors[Input, static_specs=epsilons.static_specs], weight_offsets: VariadicTensors[Input, static_specs=weight_offsets.static_specs], scales_ub: VariadicTensors[Input, static_specs=scales_ub.static_specs], dev_ctxs_input: DeviceContextList)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!