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 struct
DistributedAllReduceAddRMSNormQuantFP8
struct DistributedAllReduceAddRMSNormQuantFP8
Registers the mo.composite.distributed.allreduce_add_rms_norm_quant_fp8 graph op with the graph compiler.
Implemented traitsโ
Methodsโ
executeโ
static def execute[Outs: TypeList[Outs.values], OutScales: TypeList[OutScales.values], OutResiduals: TypeList[OutResiduals.values], Ins: TypeList[Ins.values], Sigs: TypeList[Sigs.values], Residuals: TypeList[Residuals.values], Gammas: TypeList[Gammas.values], ScalesUb: TypeList[ScalesUb.values], //, _trace_name: StaticString, epsilon: Float32, weight_offset: Float32, multiply_before_cast: Bool = True](outputs: TensorTuple[*Outs.values], outputs_scales: TensorTuple[*OutScales.values], outputs_residual: TensorTuple[*OutResiduals.values], inputs: TensorTuple[*Ins.values], signal_buffers: TensorTuple[*Sigs.values], residuals: TensorTuple[*Residuals.values], gammas: TensorTuple[*Gammas.values], scales_ub: TensorTuple[*ScalesUb.values], dev_ctxs_input: DeviceContextArray)