Skip to main content
torch.js has not been released yet.
torch.js logotorch.js logotorch.js
PlaygroundContact
Login
Documentation
IntroductionType SafetyTensor ExpressionsTensor IndexingEinsumEinopsAutogradTraining a ModelProfiling & MemoryPyTorch MigrationBest PracticesRuntimesPerformancePyTorch CompatibilityBenchmarksDType Coverage
adaptive_avg_pool1dadaptive_avg_pool2dadaptive_avg_pool3dadaptive_max_pool1dadaptive_max_pool1d_with_indicesadaptive_max_pool2dadaptive_max_pool2d_with_indicesadaptive_max_pool3dadaptive_max_pool3d_with_indicesAdaptiveMaxPoolFunctionalOptionsaffine_gridAffineGridFunctionalOptionsalpha_dropoutAlphaDropoutFunctionalOptionsavg_pool1davg_pool2davg_pool3dAvgPool1dFunctionalOptionsAvgPool2dFunctionalOptionsAvgPool3dFunctionalOptionsbatch_normBatchNormFunctionalOptionsbinary_cross_entropybinary_cross_entropy_with_logitsBinaryCrossEntropyFunctionalOptionsBinaryCrossEntropyWithLogitsFunctionalOptionsCeluFunctionalOptionschannel_shuffleconv_transpose1dconv_transpose2dconv_transpose3dconv1dConv1dFunctionalOptionsconv2dConv2dFunctionalOptionsconv3dConv3dFunctionalOptionsConvTranspose1dFunctionalOptionsConvTranspose2dFunctionalOptionsConvTranspose3dFunctionalOptionscosine_embedding_losscosine_similarityCosineEmbeddingLossFunctionalOptionsCosineSimilarityFunctionalOptionscross_entropyCrossEntropyFunctionalOptionsctc_lossCTCLossOptionsdropoutdropout1ddropout2ddropout3dDropoutFunctionalOptionsEluFunctionalOptionsembeddingembedding_bagEmbeddingBagFunctionalOptionsEmbeddingFunctionalOptionsfeature_alpha_dropoutfoldFoldFunctionalOptionsfractional_max_pool2dfractional_max_pool2d_with_indicesfractional_max_pool3dfractional_max_pool3d_with_indicesFractionalMaxPoolFunctionalOptionsgaussian_nll_lossGluFunctionalOptionsgrid_sampleGridSampleFunctionalOptionsgroup_normgrouped_mmGroupedMMFunctionalOptionsGroupNormFunctionalOptionsHardshrinkFunctionalOptionsHardtanhFunctionalOptionshinge_embedding_lossHingeEmbeddingLossFunctionalOptionshuber_lossHuberLossFunctionalOptionsinstance_normInstanceNormFunctionalOptionsinterpolateInterpolateFunctionalOptionskl_divKlDivFunctionalOptionsKLDivOptionsl1_lossL1LossFunctionalOptionslayer_normLayerNormFunctionalOptionsLeakyReluFunctionalOptionslinearlocal_response_normLocalResponseNormFunctionalOptionslog_softmaxlp_pool1dlp_pool2dlp_pool3dLPPoolFunctionalOptionsmargin_ranking_lossMarginRankingLossFunctionalOptionsmax_pool1dmax_pool1d_with_indicesmax_pool2dmax_pool2d_with_indicesmax_pool3dmax_pool3d_with_indicesmax_unpool1dmax_unpool2dmax_unpool3dMaxPool1dFunctionalOptionsMaxPool2dFunctionalOptionsMaxPool3dFunctionalOptionsMaxUnpoolFunctionalOptionsmse_lossMseLossFunctionalOptionsmulti_head_attention_forwardmulti_margin_lossMultiHeadAttentionFunctionalOptionsmultilabel_margin_lossmultilabel_soft_margin_lossnll_lossNllLossFunctionalOptionsnormalizeNormalizeFunctionalOptionsone_hotpadPadFunctionalOptionspairwise_distancePairwiseDistanceFunctionalOptionspdistPdistFunctionalOptionspixel_shufflepixel_unshufflepoisson_nll_lossPoolWithIndicesResultReluFunctionalOptionsrms_normRmsNormFunctionalOptionsRreluFunctionalOptionsscaled_grouped_mmscaled_mmScaledDotProductAttentionFunctionalOptionsScaledGroupedMMFunctionalOptionsScaledMMFunctionalOptionssmooth_l1_lossSmoothL1LossFunctionalOptionssoft_margin_lossSoftMarginLossFunctionalOptionsSoftmaxOptionsSoftminFunctionalOptionsSoftplusFunctionalOptionsSoftshrinkFunctionalOptionstriplet_margin_losstriplet_margin_with_distance_lossTripletMarginLossFunctionalOptionsunfoldUnfoldFunctionalOptionsupsampleupsample_bilinearupsample_nearestUpsampleBilinearOptionsUpsampleNearestOptionsUpsampleOptions
ActivationOptionsAdaptiveAvgPool1dAdaptiveAvgPool2dAdaptiveAvgPool3dAdaptiveLogSoftmaxOptionsAdaptiveLogSoftmaxWithLossAdaptiveMaxPool1dAdaptiveMaxPool1dOptionsAdaptiveMaxPool2dAdaptiveMaxPool2dOptionsAdaptiveMaxPool3dAdaptiveMaxPool3dOptionsadd_moduleAlphaDropoutappendappendapplyAvgPool1dAvgPool1dOptionsAvgPool2dAvgPool2dOptionsAvgPool3dAvgPool3dOptionsBackwardHookBackwardPreHookBatchNorm1dBatchNorm2dBatchNorm3dBatchNormOptionsBCELossBCEWithLogitsLossBilinearBilinearOptionsBufferBufferOptionsBufferRegistrationHookbufferscallCELUCELUOptionsChannelShufflechildrenCircularPad1dCircularPad2dCircularPad3dclearConstantPad1dConstantPad2dConstantPad3dConv1dConv2dConv3dConvOptionsConvTranspose1dConvTranspose2dConvTranspose3dConvTransposeOptionsCosineEmbeddingLossCosineEmbeddingLossOptionsCosineSimilarityCosineSimilarityOptionscreatecreateCrossEntropyLossCTCLossdecodedecodedeleteDropoutDropout1dDropout2dDropout3dDropoutOptionsELUELUOptionsEmbeddingEmbeddingBagEmbeddingBagForwardOptionsEmbeddingBagFromPretrainedOptionsEmbeddingBagOptionsEmbeddingFromPretrainedOptionsEmbeddingOptionsencodeencodeentriesentriesevalextendFeatureAlphaDropoutFlattenFlattenOptionsFoldFoldOptionsforwardforwardforwardforwardforwardforwardforwardforwardforwardforwardforwardforwardforward_with_targetForwardHookForwardPreHookFractionalMaxPool2dFractionalMaxPool3dFractionalMaxPoolOptionsfrom_pretrainedfrom_pretrainedGaussianNLLLossGELUGELUOptionsgenerate_square_subsequent_maskgetgetgetgetgetget_bufferget_parameterget_submoduleGLUGLUOptionsGroupNormGroupNormOptionsGRUGRUCellHardshrinkHardshrinkOptionsHardsigmoidHardswishHardtanhHardtanhOptionshashasHingeEmbeddingLossHingeEmbeddingLossOptionsHuberLossHuberLossOptionsIdentityInstanceNorm1dInstanceNorm2dInstanceNorm3dInstanceNormOptionsis_uninitialized_bufferis_uninitialized_parameteriterator]iterator]iterator]iterator]keyskeysKLDivLossL1LossL1LossOptionsLayerNormLayerNormOptionsLazyBatchNorm1dLazyBatchNorm2dLazyBatchNorm3dLazyConv1dLazyConv2dLazyConv3dLazyConvOptionsLazyConvTranspose1dLazyConvTranspose2dLazyConvTranspose3dLazyConvTransposeOptionsLazyInstanceNorm1dLazyInstanceNorm2dLazyInstanceNorm3dLazyLinearLeakyReLULeakyReLUOptionsLinearLinearOptionsload_state_dictload_state_dictLocalResponseNormLocalResponseNormOptionslog_probLogSigmoidLogSoftmaxLogSoftmaxOptionsLPPool1dLPPool1dOptionsLPPool2dLPPool2dOptionsLPPool3dLPPool3dOptionsLSTMLSTMCellLSTMCellOptionsMarginRankingLossMarginRankingLossOptionsmaterializematerializematerialize_uninitializedmaterialize_uninitializedMaxPool1dMaxPool1dOptionsMaxPool2dMaxPool2dOptionsMaxPool3dMaxPool3dOptionsMaxUnpool1dMaxUnpool1dOptionsMaxUnpool2dMaxUnpool2dOptionsMaxUnpool3dMaxUnpool3dOptionsMishModuleModuleBuffersModuleChildrenModuleDictModuleDictOptionsModuleListModuleListOptionsModuleParametersModuleRegistrationHookmodulesMSELossMSELossOptionsmultihead_attnMultiheadAttentionMultiheadAttentionOptionsMultiheadAttnOptionsMultiLabelMarginLossMultiLabelMarginLossOptionsMultiLabelSoftMarginLossMultiMarginLossnamed_buffersnamed_childrennamed_modulesnamed_parametersNamedModulesOptionsNamedRecurseOptionsNLLLossnum_parametersNumParametersOptionsPairwiseDistancePairwiseDistanceOptionsParameterParameterDictParameterDictOptionsParameterListParameterListOptionsParameterOptionsParameterRegistrationHookparametersPixelShufflePixelUnshufflePoissonNLLLosspoppopPReLUPReLUOptionsRecurseOptionsReflectionPad1dReflectionPad2dReflectionPad3dregister_backward_hookregister_bufferregister_forward_hookregister_forward_pre_hookregister_full_backward_hookregister_full_backward_pre_hookregister_module_backward_hookregister_module_buffer_registration_hookregister_module_forward_hookregister_module_forward_pre_hookregister_module_full_backward_hookregister_module_full_backward_pre_hookregister_module_module_registration_hookregister_module_parameter_registration_hookregister_parameterReLUReLU6RemovableHandleremoveReplicationPad1dReplicationPad2dReplicationPad3dRMSNormRMSNormOptionsRNNRNNBaseRNNBaseOptionsRNNCellRNNCellOptionsRReLURReLUOptionsrunrunSELUSequentialsetsetsetSigmoidSiLUSmoothL1LossSmoothL1LossOptionsSoftMarginLossSoftMarginLossOptionsSoftmaxSoftmax2dSoftmaxOptionsSoftminSoftminOptionsSoftplusSoftplusOptionsSoftshrinkSoftshrinkOptionsSoftsignstate_dictstate_dictStateDictOptionsstepSyncBatchNormTanhTanhshrinkThresholdThresholdOptionstotototrainTrainOptionsTransformerTransformerDecoderTransformerDecoderDecodeOptionsTransformerDecoderLayerTransformerDecoderLayerDecodeOptionsTransformerDecoderLayerOptionsTransformerDecoderOptionsTransformerEncoderTransformerEncoderEncodeOptionsTransformerEncoderLayerTransformerEncoderLayerEncodeOptionsTransformerEncoderLayerOptionsTransformerEncoderOptionsTransformerOptionsTransformerRunOptionsTripletMarginLossTripletMarginWithDistanceLossUnflattenUnfoldUnfoldOptionsUninitializedBufferUninitializedOptionsUninitializedParameterupdateUpsampleUpsamplingBilinear2dUpsamplingNearest2dvaluesvalueszero_gradZeroPad1dZeroPad2dZeroPad3d
absacosacoshAdaptivePool1dShapeAdaptivePool2dShapeaddaddbmmAddbmmOptionsaddcdivAddcdivOptionsaddcmulAddcmulOptionsaddmmAddmmOptionsaddmvAddmvOptionsaddrAddrOptionsadjointallallcloseAllcloseOptionsAlphaBetaOptionsamaxaminaminmaxAminmaxOptionsangleanyapplyOutarangeare_deterministic_algorithms_enabledargmaxargminargsortargwhereas_stridedas_tensorasinasinhAssertNoShapeErrorAssertNotErrorAsStridedOptionsAtat_error_index_out_of_boundsatanatan2atanhatleast_1datleast_2datleast_3dAtShapeautocast_decrement_nestingautocast_increment_nestingautograd_gradient_mismatch_errorautograd_not_registered_errorAutogradConfigAutogradDeviceAutogradDTypeAutogradEntryAutogradHandleAutogradHandleImplAxesRecordBackwardFnbaddbmmBaddbmmOptionsbartlett_windowBaseKernelConfigbatch_dimensions_do_not_match_errorbernoulliBernoulliOptionsBinaryBackwardFnBinaryBroadcastResultBinaryDTypeBinaryKernelConfigCPUBinaryKernelCPUBinaryOpConfigBinaryOpNamesBinaryOpSchemaBinaryOptionsbincountBincountOptionsbitwise_andbitwise_left_shiftbitwise_notbitwise_orbitwise_right_shiftbitwise_xorblackman_windowblock_diagbmmBooleanDTypeRulebroadcast_error_incompatible_dimensionsbroadcast_shapesbroadcast_tensorsbroadcast_toBroadcastShapeBroadcastShapeRulebroadcastShapesbucketizeBucketizeOptionsBufferUsagebuildEinopsErrorbuildErrorMessagecanBroadcastTocartesian_prodcatCatOptionsCatShapeCauchyOptionscdistCdistOptionsceilceluCeluFunctionalOptionschain_matmulCheckShapeErrorCholeskyShapechunkchunk_error_dim_out_of_rangeChunkOptionsclampClampOptionsclear_autocast_cacheclearEinopsCacheclearEinsumCacheclonecolumn_stackcombinationsCombinationsOptionscompiled_with_cxx11_abicomplexconjconj_physicalcontiguousConv1dShapeConv2dShapeConv3dShapeConvTranspose2dShapecopysigncorrcoefcoscoshcount_nonzeroCountNonzeroOptionscovcoverage_reportcoverageReportCoverageReportCovOptionsCPUForwardFnCPUKernelConfigCPUKernelEntryCPUOnlyResultCPUTensorDatacreateCumExtremeResultcreateTorchCreationOpSchemaCumExtremeResultcummaxcummincumprodCumShapecumsumcumulative_trapezoidCumulativeOptionsCumulativeOptionsWithDimdeg2raddetachDeterministicOptionsDetShapeDevicedevice_error_requiresDeviceBufferDeviceCapabilitiesDeviceCheckedResultDeviceConfigDeviceContextDeviceEntryDeviceHandleDeviceInputDeviceOptionsDeviceRegistryDeviceTypediagdiag_embedDiagEmbedOptionsdiagflatDiagflatOptionsDiagFlatOptionsdiagonal_scatterDiagonalOptionsDiagonalScatterOptionsDiagOptionsDiagShapediffDiffOptionsdigammadimension_error_out_of_rangeDispatchConfigdistDistOptionsdivdotDotShapeRuleDoubleDoubleDimdropoutDropoutFunctionalOptionsdsplitdstackDTypedtype_already_registered_errordtype_components_mismatch_errordtype_not_found_errorDTypeComponentsDTypeConfigDTypeCoverageReportDTypeDisplayConfigDTypeEntryDTypeHandleDTypeHandleImplDTypeInfoDTypeRegistryDTypeRuleDTypeSerializationConfigDynamicShapeEigShapeeinops_error_ambiguous_decompositioneinops_error_anonymous_in_outputeinops_error_dimension_mismatcheinops_error_invalid_patterneinops_error_reduce_undefined_outputeinops_error_repeat_missing_sizeeinops_error_undefined_axiseinsumeinsum_error_dimension_mismatcheinsum_error_index_out_of_rangeeinsum_error_invalid_equationeinsum_error_invalid_sublist_elementeinsum_error_operand_count_mismatcheinsum_error_subscript_rank_mismatcheinsum_error_unknown_output_indexEinsumOptionsEinsumOutputShapeEllipsiseluelu_EluFunctionalOptionsembedding_bag_error_requires_2d_inputemptyempty_cacheempty_likeeqequalerferfcerfinvexpexp2expandexpand_asexpand_error_incompatibleExpandShapeexpm1ExponentialOptionseyeEyeOptionsfftFFTOptionsfindKernelWithPredicatefindSimilarPatternsflattenFlattenOptionsFlattenShapeflipflip_error_dim_out_of_rangefliplrFlipShapeflipudfloat_powerFloatDTypeRulefloorfloor_dividefmaxfminfmodformatEquationErrorformatShapefracfrexpfrombufferfullfull_likefunction_already_registered_errorFunctionConfigFunctionEntryFunctionHandlegathergather_error_dim_out_of_rangeGatherShapegcdgegeluGeometricOptionsget_autocast_cpu_dtypeget_autocast_gpu_dtypeget_autocast_ipu_dtypeget_autocast_xla_dtypeget_default_deviceget_default_dtypeget_deterministic_debug_modeget_device_configget_device_contextget_device_moduleget_dtype_infoget_file_pathget_float32_matmul_precisionget_num_interop_threadsget_num_threadsget_op_infoget_printoptionsget_real_dtypeget_rng_stategetAutogradgetDTypegetEinopsCacheSizegetEinsumCacheSizegetFunctiongetKernelgetMethodgetOpInfoGetOpKindGetOpSchemagetScalarKernelgluGluFunctionalOptionsGradContextGradFnGradientsForgtHalfHalfDimhamming_windowhann_windowhardshrinkhardsigmoidhardswishhardtanhhardtanh_HardtanhFunctionalOptionshas_autogradhas_devicehas_dtypehas_kernelhasAutogradhasDTypehasFunctionhasKernelhasMethodhasScalarKernelHasShapeErrorheavisidehistcHistcOptionshistogramHistogramOptionsHistogramResulthsplithstackhypoti0IdentityShapeifftimagindex_addindex_copyindex_fillindex_putindex_reduceindex_selectindex_select_error_dim_out_of_rangeIndexPutOptionsIndexSelectShapeIndexSpecIndicesOptionsIndicesSpecinitialize_deviceInputsForInsertDiminvalid_config_errorinverseInverseShapeirfftis_anomaly_check_nan_enabledis_anomaly_enabledis_autocast_cache_enabledis_autocast_cpu_enabledis_autocast_ipu_enabledis_autocast_xla_enabledis_complexis_complex_dtypeis_cpu_only_modeis_deterministic_algorithms_warn_only_enabledis_floating_pointis_floating_point_dtypeis_inference_mode_enabledis_nonzerois_tensoris_warn_always_enabledis_webgpu_availableIs2DIsAtLeast1DIsBinaryOpIsBinaryOpNameiscloseIscloseOptionsisfiniteisinisinfisnanisneginfisposinfisrealIsReductionOpIsReductionOpNameIsRegistryErrorIsShapeErroristftISTFTOptionsIsUnaryOpIsUnaryOpNameitem_error_not_scalarItemResultkaiser_windowKaiserWindowOptionskernel_not_registered_errorkernel_signature_mismatch_errorKernelConfigKernelConfigWebGPUKernelEntryKernelHandleKernelInfoKernelPredicateKernelRegistryKernelWebGPUkronkthvalueKthvalueOptionslcmldexpleleaky_reluleaky_relu_LeakyReluFunctionalOptionslerplevenshteinDistancelgammalinalg_error_not_square_matrixlinalg_error_requires_2dlinalg_error_requires_at_least_2dlinearlinspacelist_custom_deviceslist_custom_dtypeslist_deviceslist_dtypeslist_functionslist_kernelslist_methodslist_opslistCustomDTypeslistDTypeslistFunctionslistKernelsListKernelsOptionslistMethodslistOpsListOpsOptionsloglog_softmaxlog10log1plog2logaddexplogaddexp2logcumsumexplogical_andlogical_notlogical_orlogical_xorLogitOptionsLogNormalOptionsLogOptionslogsigmoidlogspacelogsumexpLogsumexpOptionsltLUShapeLuSolveOptionsmasked_fillmasked_selectmasked_select_asyncMaskSpecmatmulmatmul_error_inner_dimensions_do_not_matchMatmul2DShapeMatmulShapeMatmulShapeRuleMatrixTransposeShapemaxmaximummeanmedianmemory_statsmemory_summarymeshgridmethod_already_registered_errormethod_dtype_not_supported_errorMethodConfigMethodEntryMethodHandleminminimummishmmMMShapeRulemodemovedimmsortmulmultinomialmultinomial_asyncMultinomialAsyncOptionsMultinomialOptionsMultiplyBymvMVShapeRulenan_to_numnanmeannanmediannanquantileNanReductionOptionsnansumNanToNumOptionsnarrownarrow_copynarrow_error_length_exceeds_boundsnarrow_error_start_out_of_boundsNarrowShapeneneedsBroadcastnegNegativeDimnextafternonzeroNonzeroOptionsnormnormalNormalOptionsNormOptionsnumelonesones_likeop_kind_mismatch_errorop_not_found_errorOpCoverageEntryOpInfoOpKindOpNameOpSchemaOpSchemasouterOuterShapepackPackShapepermutepermute_error_dimension_count_mismatchPermuteShapepoissonpolarPool1dShapePool2dShapePool3dShapepositivepowpreluPrintOptionsprodprofiler_allow_cudagraph_cupti_lazy_reinit_cuda12promote_typesPromoteDTypeRulePutOptionsquantileQuantileOptionsrad2degrandrand_likerandintrandint_likeRandintLikeOptionsRandintOptionsrandnrandn_likeRandomLikeOptionsRandomOptionsrandpermRangeSpecRankravelrealrearrangeRearrangeOptionsRearrangeShapereciprocalreduceReduceOperationReduceOptionsReduceShapeReductionKernelConfigCPUReductionKernelCPUReductionOpNamesReductionOpSchemaReductionOptionsReductionShapeRuleregister_backwardregister_deviceregister_dtyperegister_forwardregister_functionregister_methodregister_scalar_forwardregisterAutogradRegisterBackwardOptionsregisterBinaryOpregisterDTypeRegisterDTypeOptionsRegisteredDTyperegisterFunctionRegisterFunctionOptionsregisterKernelRegisterKernelOptionsregisterMethodRegisterMethodOptionsregisterScalarKernelregisterUnaryOpregistration_failed_errorrelurelu_relu6ReluFunctionalOptionsremainderRemoveDimrepeatrepeat_interleaveRepeatInterleaveOptionsRepeatOptionsRepeatShapeReplaceDimrequireWebGPUreset_peak_memory_statsreshapeReshapeShaperesult_typerfftrollRollOptionsrot90Rot90Optionsroundrrelurrelu_RreluFunctionalOptionsrsqrtSafeExpandShapeSameDTypeRuleSameShapeRuleSaveForBackwardScalarCPUForwardFnScalarCPUKernelConfigScalarKernelEntryScalarKernelHandleScalarWebGPUKernelConfigScaleDimscatterscatter_addscatter_add_scatter_error_dim_out_of_rangescatter_reducescatter_reduce_ScatterReduceOptionsScatterShapesearchsortedSearchSortedOptionsselectselect_error_index_out_of_boundsselect_scatterSelectShapeseluset_default_deviceset_default_tensor_typeset_deterministic_debug_modeset_float32_matmul_precisionset_printoptionsset_warn_alwaysSetupContextFnShapeShapeCheckedResultShapedTensorShapeErrorMessageShapeOpSchemaShapeRulesigmoidsignsignbitsilusinsincsinhSizeOptionsslice_error_out_of_boundsslice_scatterSliceOptionsSliceScatterOptionsSliceShapeSliceSpecsoftmaxsoftmax_error_dim_out_of_rangeSoftmaxShapesoftminSoftminFunctionalOptionssoftplusSoftplusFunctionalOptionssoftshrinksoftsignsortSortOptionssplitsplit_error_dim_out_of_rangeSplitOptionssqrtsquaresqueezeSqueezeOptionsSqueezeShapestackStackOptionsStackShapestdstd_meanStdVarMeanOptionsStdVarOptionsstftSTFTOptionsStrideOptionssubSublistSublistElementSubscriptIndexsumSVDShapeswapaxessym_floatsym_intsym_notttaketake_along_dimTakeAlongDimOptionstantanhtanhshrinktensortensor_splitTensorCreatorTensorDatatensordotTensordotOptionsTensorLikeTensorMetaTensorOptionsTensorStoragethresholdthreshold_tileTileShapeToOptionstopkTopkOptionsTorchtraceTraceShapetransposetranspose_dims_error_out_of_rangetranspose_error_requires_2d_tensorTransposeDimsShapeTransposeDimsShapeCheckedTransposeShapetrapezoidTrapezoidOptionsTriangularOptionstriltril_indicesTriOptionsTripletriutriu_indicestrue_dividetruncTupleOfLengthTypedArrayTypedArrayForTypedStorageTypeOptionsUnaryBackwardFnUnaryDTypeUnaryKernelConfigCPUUnaryKernelCPUUnaryOpConfigUnaryOpFnUnaryOpNamesUnaryOpParamsUnaryOpSchemaUnaryOptionsunbindunbind_error_dim_out_of_rangeUnbindOptionsunflattenUniformOptionsuniqueunique_consecutiveUniqueConsecutiveOptionsUniqueOptionsunpackUnpackShapeunravel_indexunregister_deviceunsqueezeUnsqueezeOptionsUnsqueezeShapeuse_deterministic_algorithmsValidateBatchedSquareMatrixValidateChunkDimValidatedEinsumShapevalidateDeviceValidateDeviceValidatedRearrangeShapeValidatedReduceShapeValidatedRepeatShapevalidateDTypeValidateEinsumValidateOperandCountValidateRanksValidateScalarValidateSplitDimValidateSquareMatrixValidateUnbindDimValueOptionsvar_var_meanvdotviewview_as_complexview_as_realvmapvsplitvstackWebGPUKernelConfigWebGPUOnlyResultWebGPUTensorDatawhereWindowOptionsxlogyzeroszeros_like
torch.js· 2026
LegalTerms of UsePrivacy Policy
/
/
  1. docs
  2. torch.js
  3. torch
  4. nn
  5. functional
  6. scaled_grouped_mm

torch.nn.functional.scaled_grouped_mm

function scaled_grouped_mm(input: Tensor, weight: Tensor, options?: ScaledGroupedMMFunctionalOptions): Tensor

Performs batched (grouped) matrix multiplication with per-batch scaling.

Computes batched matrix multiplication where each batch element is independently multiplied and then scaled by a single factor. More memory-efficient than grouped_mm for regular batched operations. Essential for:

  • Batched transformations: Processing batch of matrices in parallel
  • Quantized operations: Scale by per-group quantization factors
  • Attention scaling: Q @ K^T with 1/√d scaling in transformer attention
  • Efficient inference: Single scale applied uniformly across batch
  • Multi-sample processing: Processing multiple matrices simultaneously
  • GPU acceleration: Leverages batch matmul optimization
  • Fixed quantization: Constant scaling factor for all batch items

Operation: For 3D tensors: output[b] = (input[b] @ weight[b]) * scale

The same scale factor is applied to all batch elements after multiplication, useful for learnable scaling or quantized inference.

Difference from grouped_mm:

  • scaled_grouped_mm: Single scale for all batches (uses bmm)
  • grouped_mm: Different weights and potentially biases per group
  • Performance: scaled_grouped_mm optimized for batched matmul
  • Batch matmul optimization: Uses GPU batch matmul for efficiency
  • Single scale: Same scale applied to entire batch (vs grouped_mm's per-group)
  • 3D tensors only: Input and weight must be 3D [batch, *, *]
  • Batch sizes must match: input.shape[0] must equal weight.shape[0]
  • Inner dimensions match: input.shape[2] must equal weight.shape[1]
  • Scale=1 optimization: Returns unscaled result directly when scale=1.0
  • Gradient propagation: Gradients flow to input and weight tensors
  • Attention standard: Common pattern for transformer attention
  • Invalid dimensions: Must have exactly 3D input and weight tensors
  • Batch size mismatch: Batch dimensions must be identical
  • Inner dimension mismatch: k dimensions must match for matmul
  • Scale interpretation: Scale is multiplicative (not additive)

Parameters

inputTensor
Input tensor of shape [batch, m, k] - batch: Number of independent matrix multiplications - m: Number of rows in each batch element - k: Number of columns (inner dimension for matmul)
weightTensor
Weight tensor of shape [batch, k, n] - batch: Must match input batch size - k: Must match input's last dimension (k) - n: Number of output columns
optionsScaledGroupedMMFunctionalOptionsoptional

Returns

Tensor– Tensor of shape [batch, m, n] containing scaled batched matmul result

Examples

// Attention scaling: Q @ K^T / sqrt(d)
const batch_size = 32;
const seq_len = 10;
const head_dim = 64;

const queries = torch.randn(batch_size, seq_len, head_dim);     // Q
const keys = torch.randn(batch_size, seq_len, head_dim);         // K^T
const scale = 1.0 / Math.sqrt(head_dim);  // 1/√64 ≈ 0.125

const attn_scores = torch.nn.functional.scaled_grouped_mm(queries, keys, scale);
// attn_scores: [32, 10, 10] - attention scores scaled by 1/√64
// Batched matrix multiplication with quantization scale
const input = torch.randn(16, 128, 256);   // [batch, m, k]
const weights = torch.randn(16, 256, 128); // [batch, k, n]
const quant_scale = 0.1;  // Quantization factor

const output = torch.nn.functional.scaled_grouped_mm(input, weights, quant_scale);
// output: [16, 128, 128] scaled by 0.1
// Batch processing with learnable scale
const batch = torch.randn(8, 100, 50);
const weights = torch.randn(8, 50, 30);
const learnable_scale = torch.tensor(1.5, { requires_grad: true });

const output = torch.nn.functional.scaled_grouped_mm(batch, weights, learnable_scale.item());
// Scale is learnable through backprop
// Multi-head attention implementation
const batch = 32, heads = 8, seq = 10, dim = 64;
// Reshape [batch, seq, heads*dim] → [batch*heads, seq, dim] for faster matmul
const Q = torch.randn(batch * heads, seq, dim);
const K = torch.randn(batch * heads, seq, dim);

const scale = 1.0 / Math.sqrt(dim);
const attention = torch.nn.functional.scaled_grouped_mm(Q, K, scale);
// attention: [batch*heads, seq, seq]
// No scaling optimization: scale=1.0 is efficient
const input = torch.randn(64, 256, 512);
const weights = torch.randn(64, 512, 256);

const result = torch.nn.functional.scaled_grouped_mm(input, weights, 1.0);
// Equivalent to input @ weights, no-op scaling

See Also

  • [PyTorch torch.nn.functional._scaled_grouped_mm (internal)](https://pytorch.org/docs/stable/generated/torch.nn.functional._scaled_grouped_mm .html)
  • grouped_mm - Grouped matmul with independent weights per group
  • scaled_mm - General scaled matrix multiplication with advanced options
  • Tensor.bmm - Batched matrix multiplication without scaling
  • Tensor.matmul - General matrix multiplication
Previous
RreluFunctionalOptions
Next
scaled_mm