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
Registers the mo.composite.distributed.allreduce_add_rms_norm_quant_fp8 graph op with the graph compiler.
Implemented traits
Methods
execute
static def execute[dtype: DType, output_type: DType, scales_type: DType, rank: Int, target: StringSlice[ImmStaticOrigin], _trace_name: StringSlice[ImmStaticOrigin]](outputs: VariadicTensors[IOSpec[_, _].Output, static_specs=outputs.static_specs], outputs_scales: VariadicTensors[IOSpec[_, _].Output, static_specs=outputs_scales.static_specs], outputs_residual: VariadicTensors[IOSpec[_, _].Output, static_specs=outputs_residual.static_specs], inputs: VariadicTensors[IOSpec[_, _].Input, static_specs=inputs.static_specs], signal_buffers: VariadicTensors[IOSpec[_, _].MutableInput, static_specs=signal_buffers.static_specs], residuals: VariadicTensors[IOSpec[_, _].Input, static_specs=residuals.static_specs], gammas: VariadicTensors[IOSpec[_, _].Input, static_specs=gammas.static_specs], epsilons: VariadicTensors[IOSpec[_, _].Input, static_specs=epsilons.static_specs], weight_offsets: VariadicTensors[IOSpec[_, _].Input, static_specs=weight_offsets.static_specs], scales_ub: VariadicTensors[IOSpec[_, _].Input, static_specs=scales_ub.static_specs], dev_ctxs_input: DeviceContextArray)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!