Skip to content

Backend Operator Support Report

This file is generated from converter sources by scripts/generate_backend_operator_report.py. Do not edit this file manually. Run make docs-backend-ops after backend changes.

ONNX Runtime Backend

  • Converter source: src/converters/onnx.rs
  • Executor source: src/executors/onnx.rs
  • Converter operator count: 0
  • Executor operator count: 0

Converter Operators

  • (none)

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • (none)

CoreML MLProgram Backend

  • Converter source: src/converters/coreml_mlprogram.rs
  • Executor source: src/executors/coreml.rs
  • Converter operator count: 88
  • Executor operator count: 88

Converter Operators

  • abs, hardSigmoid, reducemin
  • add, hardSwish, reduceproduct
  • argMax, identity, reducesum
  • argMin, instanceNormalization, reducesumsquare
  • averagePool2d, layerNormalization, relu
  • batchNormalization, leakyRelu, reshape
  • cast, lesser, reverse
  • ceil, lesserOrEqual, roundEven
  • clamp, log, scatterElements
  • concat, logicalAnd, scatterND
  • conv2d, logicalNot, sigmoid
  • convTranspose2d, logicalOr, sign
  • cos, logicalXor, sin
  • cumulativeSum, matmul, slice
  • dequantizeLinear, max, softmax
  • div, maxPool2d, softplus
  • elu, min, softsign
  • equal, mul, split
  • erf, neg, sqrt
  • exp, pad, squeeze
  • expand, pow, sub
  • floor, prelu, tan
  • gather, quantizeLinear, tanh
  • gatherElements, reciprocal, tile
  • gelu, reducel1, transpose
  • gemm, reducel2, triangular
  • globalAveragePool, reducelogsum, unsqueeze
  • globalMaxPool, reducelogsumexp, where
  • greater, reducemax
  • greaterOrEqual, reducemean

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • abs, hardSigmoid, reducemin
  • add, hardSwish, reduceproduct
  • argMax, identity, reducesum
  • argMin, instanceNormalization, reducesumsquare
  • averagePool2d, layerNormalization, relu
  • batchNormalization, leakyRelu, reshape
  • cast, lesser, reverse
  • ceil, lesserOrEqual, roundEven
  • clamp, log, scatterElements
  • concat, logicalAnd, scatterND
  • conv2d, logicalNot, sigmoid
  • convTranspose2d, logicalOr, sign
  • cos, logicalXor, sin
  • cumulativeSum, matmul, slice
  • dequantizeLinear, max, softmax
  • div, maxPool2d, softplus
  • elu, min, softsign
  • equal, mul, split
  • erf, neg, sqrt
  • exp, pad, squeeze
  • expand, pow, sub
  • floor, prelu, tan
  • gather, quantizeLinear, tanh
  • gatherElements, reciprocal, tile
  • gelu, reducel1, transpose
  • gemm, reducel2, triangular
  • globalAveragePool, reducelogsum, unsqueeze
  • globalMaxPool, reducelogsumexp, where
  • greater, reducemax
  • greaterOrEqual, reducemean

TensorRT Backend

  • Converter source: src/converters/trtx.rs
  • Executor source: src/executors/trtx.rs
  • Converter operator count: 95
  • Executor operator count: 95

Converter Operators

  • abs, hardSwish, reduceMax
  • add, identity, reduceMean
  • argMax, instanceNormalization, reduceMin
  • argMin, isInfinite, reduceProduct
  • averagePool2d, isNaN, reduceSum
  • batchNormalization, l2Pool2d, reduceSumSquare
  • cast, layerNormalization, relu
  • ceil, leakyRelu, resample2d
  • clamp, lesser, reshape
  • concat, lesserOrEqual, reverse
  • conv2d, linear, roundEven
  • convTranspose2d, log, scatterElements
  • cos, logicalAnd, scatterND
  • cumulativeSum, logicalNot, sigmoid
  • dequantizeLinear, logicalOr, sign
  • div, logicalXor, sin
  • elu, matmul, slice
  • equal, max, softmax
  • erf, maxPool2d, softplus
  • exp, min, softsign
  • expand, mul, split
  • floor, neg, sqrt
  • gather, notEqual, squeeze
  • gatherElements, pad, sub
  • gatherND, pow, tan
  • gelu, prelu, tanh
  • gemm, quantizeLinear, tile
  • globalAveragePool, reciprocal, transpose
  • globalMaxPool, reduceL1, triangular
  • greater, reduceL2, unsqueeze
  • greaterOrEqual, reduceLogSum, where
  • hardSigmoid, reduceLogSumExp

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • abs, hardSwish, reduceMax
  • add, identity, reduceMean
  • argMax, instanceNormalization, reduceMin
  • argMin, isInfinite, reduceProduct
  • averagePool2d, isNaN, reduceSum
  • batchNormalization, l2Pool2d, reduceSumSquare
  • cast, layerNormalization, relu
  • ceil, leakyRelu, resample2d
  • clamp, lesser, reshape
  • concat, lesserOrEqual, reverse
  • conv2d, linear, roundEven
  • convTranspose2d, log, scatterElements
  • cos, logicalAnd, scatterND
  • cumulativeSum, logicalNot, sigmoid
  • dequantizeLinear, logicalOr, sign
  • div, logicalXor, sin
  • elu, matmul, slice
  • equal, max, softmax
  • erf, maxPool2d, softplus
  • exp, min, softsign
  • expand, mul, split
  • floor, neg, sqrt
  • gather, notEqual, squeeze
  • gatherElements, pad, sub
  • gatherND, pow, tan
  • gelu, prelu, tanh
  • gemm, quantizeLinear, tile
  • globalAveragePool, reciprocal, transpose
  • globalMaxPool, reduceL1, triangular
  • greater, reduceL2, unsqueeze
  • greaterOrEqual, reduceLogSum, where
  • hardSigmoid, reduceLogSumExp