# QNN HTP Op Support Revision History | Introduced in QNN SDK Version | Runtime | Description | | --- | --- | --- | | 2.49.0 | Quant |

FullyConnected (Activation type: INT8)
- Enabled a8w2 per-channel quantized support

ElementWiseMux expanded supported dtypes (INT8/INT16/FP16)

MaskedSoftmax added to INT8 and INT16 supported ops

GroupedQueryAttention (GQA) added to INT8, INT16, FP16, and All supported ops

Updated IMPL_GENERATED op validation constraints (INT8/INT16)

| | 2.48.0 | Quant |

ElementWiseMux added to INT8 supported ops

RandomNormalLike added to INT16 supported ops

Conv2d, TransposeConv2d (Activation type: FP16/INT16)
- Added per-channel and FP updateable tensor support

Conv2d, FullyConnected, MatMul (Activation type: FP16)
- Updated FP16W8 constraints and MXFP4/PCQ conversion support

Added Firewheel op validation support for INT16 ops

ScatterElements (Activation type: INT32)
- Enabled MUL reduction mode

| | 2.47.0 | Quant |

RandomNormalLike added to FP16 supported ops

RandomUniformLike moved from Others to INT8 supported ops

Conv2d, FullyConnected, MatMul (Activation type: FP16)
- Enabled W8/W4/W2 FP16-activation Block Quantization (BW_FLOAT_BLOCK encoding)

ScatterElements (Activation type: INT32)
- Enabled ADD and MAX reduction modes

HadamardTransform added to INT16 supported ops

Conv2d (Activation type: INT16)
- Relaxed IMPL_GENERATED dilation constraint for a16w8 configurations

Conv-Relu fusion validation warning added when output quantization range exceeds
ReluMinMax bounds

| | 2.46.0 | Quant |

Conv2d (Activation type: INT8)
- Added per-channel multi-quant support

FullyConnected, MatMul (Activation type: FP16)
- Updated block quantization (BQ) not-supported constraints

ScatterElements with None reduction type enabled on INT32

| | 2.45.0 | Quant |

RotaryEmbedding added to supported ops (ROPE)

Gru (Activation type: INT16)
- Enabled a16w16 configuration; only forward direction is supported

TransposeConv2d
- Added updateable quantization support

ElementWiseExp, ReluMinMax (Activation type: FP16/FP32)
- Increased max supported rank to 5

ElementWiseUnary, ElementWiseNeuron constraints updated

| | 2.44.0 | Quant |

ElementWiseBinary DIVIDE enabled on QNN_DATATYPE_SFIXED_POINT_8

Buffer enabled on QNN_DATATYPE_UFIXED_POINT_16, QNN_DATATYPE_UFIXED_POINT_8

Cast enabled on QNN_DATATYPE_SFIXED_POINT_16 to QNN_DATATYPE_INT_32

Lstm (Activation type: INT8, INT16)
- Added support for a16w16 and a16w8 configurations

Conv2d (Activation type: INT16)
- Added support for 4-bit weights

ElementWiseUnary Exp enabled on BF16

RmsNorm enabled on BF16

| | 2.43.0 | Quant |

Gelu (Activation type: All)
- Enabled 5D FP16/FP32 validation
- Adjusted 4D rank constrain

Conv2d
- Enabled updateable quantization support on FP16, INT16
- Added custom symmetric 2-bit weights support on INT16

L2Norm enabled on INT16

Prelu, Relu, Relu1, Relu6, ReluMinMax, Batchnorm, ElementWiseExp enabled on BF16

| | 2.42.0 | Quant |

Lstm (Activation type: INT8)
- Added LayerNorm unsupport constraints for 3D input and remove forward direction limit

HadamardTransform enabled on INT16

ElementwiseDividem, ElementwiseMaximum enabled on INT16

Convert enabled on FP16 to SFIXED_POINT

ReduceMin added to supported ops

| | 2.41.0 | Quant |

Conv3d (Activation type: INT8, INT16)
- Added Conv3d to Relu IMPL_GEN tensor support

Conv2d (Activation type: INT8, INT16)
- Removed group constraint with IMPL_GEN tensor
- Added support for Conv2d to Relu on a16w16
- Added QNN_QUANTIZATION_ENCODING_FLOAT_BLOCK encoding support for in[1]

Convert (Activation type: INT16)
- Added support for QNN_DATATYPE_SFIXED_POINT_16 to QNN_DATATYPE_FLOAT_16

Added ElementWiseMod on QNN_DATATYPE_INT_32

| | 2.40.0 | Quant |

Conv2d (Activation type: FP16)
- Added width and height constraints for in[1]

GridSample enabled on QNN_DATATYPE_INT_32

| | 2.39.0 | Quant |

Logit enabled on all activation type.

ScatterElements (Activation type: INT8, INT16)
- Enabled updateable tensor support

DepthWiseConv2d (Activation type: INT8, INT16)
- Added QNN_DEFINITION_IMPL_GENERATED constraint

ElementWiseSqrt enabled on QNN_DATATYPE_SFIXED_POINT_16

Convert (Activation type: INT16)
- Enabled QNN_DATATYPE_UFIXED_POINT_16, QNN_DATATYPE_UFIXED_POINT_8,
  QNN_DATATYPE_SFIXED_POINT_8 for out[0]

Dequantize enabled QNN_DATATYPE_FLOAT_16 for out[0]

Quantize (Activation type: INT16, INT8)
- Enabled on QNN_DATATYPE_FLOAT_16 to QNN_DATATYPE_UFIXED_POINT_16
- Enabled on QNN_DATATYPE_FLOAT_16 to QNN_DATATYPE_SFIXED_POINT_16
- Enabled on QNN_DATATYPE_FLOAT_16 to QNN_DATATYPE_UFIXED_POINT_8
- Enabled on QNN_DATATYPE_FLOAT_16 to QNN_DATATYPE_SFIXED_POINT_8

ElementWiseSelect, ElementWiseBinary, ReduceMin, MatMul (Activation type: INT16)
- Enabled updateable tensor support

Stft enabled on QNN_DATATYPE_FLOAT_16, QNN_DATATYPE_FLOAT_32

| | 2.38.0 | Quant |

Adjust constraint message from support/not support to accept/reject.

UnPack enabled on QNN_DATATYPE_SFIXED_POINT_16

ElementWiseBinary (Activation type: INT8)
- Removed operation constraints in HTP

GatherElements, Cast, Pad added rank 5d support on all activation type

Cast enabled on QNN_DATATYPE_SFIXED_POINT_16 to QNN_DATATYPE_UFIXED_POINT_16

Quantize, enabled on QNN_DATATYPE_FLOAT_32

ElementWiseAbs enabled on QNN_DATATYPE_INT_32

ElementWiseUnary enabled on QNN_DATATYPE_INT_32

ElementWiseMaximum enabled on QNN_DATATYPE_INT_32

ElementWiseMinimum enabled on QNN_DATATYPE_INT_32

RandomUniformLike enabled on QNN_DATATYPE_UINT_32 for in[0],
QNN_DATATYPE_FLOAT_32 for in[1]

| | 2.37.0 | Quant |

Gather (Activation type: INT8)
- Added math invariant tags for out[0]

Tile (Activation type: INT8, INT16)
- Added math invariant tags for out[0]

Cast (Activation type: INT8)
- Added support from UINT8 to FP16

ChannelShuffle (Activation type: INT8, INT16)
- Added math invariant tags for out[0]

StridedSlice enabled on QNN_DATATYPE_UINT_8

TopK (Activation type: INT8)
- Added math invariant tags for out[0]

Nv12ToRgb enabled on QNN_DATATYPE_UFIXED_POINT_8

Split enabled on QNN_DATATYPE_SFIXED_POINT_16

IsNan enabled on FP16

| | 2.36.0 | Quant |

Pad (Activation type: INT16)
- Added updateable quantization support for in[0], out[0]

Gather (Activation type: FP16)
- Added updateable quantization support for in[1]

Gather (Activation type: INT8)
- Added updateable quantization support for out[0]

RmsNorm enabled on QNN_DATATYPE_SFIXED_POINT_16

Gru enabled on QNN_DATATYPE_FLOAT_16, QNN_DATATYPE_FLOAT_32

Buffer enabled on FP16

| | 2.35.0 | Quant |

Enable enabled on QNN_DATATYPE_UINT_8

Tile (Activation type: INT8, INT16)
- Added quantization constraint for in[0], out[0]

ElementWiseAsin enabled on QNN_DATATYPE_SFIXED_POINT_16

Conv2d (Activation type: IN16)
- Changed constraint for in[1]

LayerNorm (Activation type: FP16)
- Added rank constraint for in[1], in[2]

IsInf enabled on QNN_DATATYPE_FLOAT_16, QNN_DATATYPE_FLOAT_32

| | 2.34.0 | Quant |

BatchToSpace, SpaceToBatch (Activation type: INT8, INT16)
- Added math invariant constraint for out[0]

LayerNorm (Activation type: INT8, INT16)
- Adjusted rank constraint for in[2]

Tile (Activation type: INT8, INT16)
- Added 5D support for in[0], out[0]

Conv2d (Activation type: INT16)
- Updated Quant constraint for in[1]

ElementWiseNeuron (Activation type: FP16)
- Added 5D Sigmoid support for in[0], out[0]

Sigmoid (Activation type: FP16)
- Added 5D support for in[0], out[0]

| | 2.33.0 | Quant |

ElementWiseRsqrt, ElementWiseUnary, ElementWiseNeuron, Gelu (Activation type: INT16)
- Added QNN_DATATYPE_SFIXED_POINT_16 support for in[0], out[0]

ElementWiseGreater, ElementWiseGreaterEqual, ElementWiseLess, ElementWiseLessEqual,
ElementWiseNotEqual, ElementWiseBinary (Activation type: FP16)
- Added 5D support for in[0], in[1], out[0]

Concat enabled on QNN_DATATYPE_BOOL_8

| | 2.32.0 | Quant |

Reshape (Activation type: INT8, INT16)
- Removed in[1] constraint
- Added Dynamic_Shape type constraint for in[0], out[0]

ElementWiseSubtract enabled on QNN_DATATYPE_SFIXED_POINT_16

ReduceSum enabled on QNN_DATATYPE_SFIXED_POINT_16

ScatterElements (Activation type: INT8)
- Added support for max reduction

Gather (Activation type: INT8)
- Added udateable quantization support for in[0], in[1]
- Enabled on QNN_DATATYPE_SFIXED_POINT_16

Softmax enabled on QNN_DATATYPE_SFIXED_POINT_16

MatMul enabled on QNN_DATATYPE_SFIXED_POINT_16

StridedSlice enabled on QNN_DATATYPE_SFIXED_POINT_16

FullyConnected enabled on QNN_DATATYPE_SFIXED_POINT_16

Conv2d (Activation type: INT16)
- Added supplement constraints for in[1], in[2]

Split enabled on QNN_DATATYPE_BOOL_8

| | 2.31.0 | Quant |

Tanh (Activation type: INT16)
- Removed 1/32768.0 scale and 0 offset constraint for out[0]

Conv2d (Activation type: INT16)
- Added 16-bit per-channel quantization for in[1]

FullyConnected (Activation type: INT16)
- Added 16-bit per-channel quantization for in[1]

MatMul (Activation type: INT16)
- Added 16-bit per-channel quantization for in[1]

| | 2.30.0 | Quant |

Conv2d (Activation type: INT8)
- Added updateable tensor support for in[2]

Conv2d (Activation type: INT16)
- Added updateable quantization support for in[0], in[1], in[2], out[0]

RmsNorm (Activation type: INT16)
- Added dynamic tensor support on width and channel for in[0], out[0]

DepthWiseConv2d (Activation type: INT16)
- Added updateable quantization support for in[0], in[1]

| | 2.29.0 | Quant |

Dynamic tensor ops have been enabled in OpValidator

TopK (Activation type: All)
- Added support to largest parameter that largest can be equal to 0

ElementWiseNeuron (Activation type: INT8, INT16)
- Added Softplus support with rank 4d

BatchNorm, LayerNorm (Activation type: INT8)
- Added QNN_DATATYPE_SFIXED_POINT_8 support for BatchNorm and LayerNorm

Convert (Activation type: INT16)
- Added updateable quantization support for in[0] and out[0] when in[0] and out[0]
  both are QNN_DATATYPE_UFIXED_POINT_16 datatype

RmsNorm (Activation type: INT16)
- Added updateable quantization support for in[0], in[1] and in[2] when
  in[0] is QNN_DATATYPE_UFIXED_POINT_16, in[1] is QNN_DATATYPE_UFIXED_POINT_8 and
  in[2] is QNN_DATATYPE_SFIXED_POINT_32

ElementWiseBinary Equal (Activation type: FP16)
- Added rank 5d support for in[0], in[1] and out[0] for ElementWiseBinary Equal

ReduceSum (Activation type: FP16, FP32)
- Added rank 5d support for in[0] and out [0]

| | 2.28.0 | Quant |

Axes (Activation type: All)
- Added support to normalization on final dimension or last 3 diminsions of 4D inputs

Prelu (Activation type: All)
- Added rank 5d support for in[0], in[1] and out[0]

NonZero (Activation type: INT16, FP16)
- Added NonZero op support

Tile (Activation type: FP16, FP32)
- Added rank 5d support for in[0] and out [0]

RmsNorm (Activation type: INT16, INT8)
- Added updateable quantization support for in[0], in[2] and out[0]

Conv2d (Activation type:INT8)
- Added updateable quantization support for in[0], in[1] and out[0]

ElementwiseNeuron Relu (Activation type: INT8, INT16)
- Added QNN_DATATYPE_SFIXED_POINT_16 support for in[0] and out[0]

ExtractGlimpse (Activation type: INT16)
- Added ExtractGlimpse op support

Convert (Activation type: INT16)
- Added updateable quantization support for in[0] and out[0]

ElementWiseBinary (Activation type: FP16)
- Added rank 5d support for in[0], in[1] and out[0] for Add, Sub and Pow

ElementWiseUnary Sqrt (Activation type: FP16)
- Added rank 5d support for in[0] and out[0] for Sqrt

ReduceMax, ReduceMin, ReduceMean (Activation type: FP16)
- Added rank 5d support for in[0]

ElementWiseNeuron SoftPlus (Activation type: FP16)
- Added QNN_DATATYPE_FLOAT_16, QNN_DATATYPE_FLOAT_32 datatype support for in[0]
  and out[0]

ReduceMin (Activation type: INT32)
- Added ReduceMin op support with 5d rank and QNN_DATATYPE_INT_32 datatype for in [0]
  and out[0]

| | 2.27.0 | Quant |

ElementWiseNeuron, Sigmoid (Activation type: All)
- Added constraint that dynamic dimensions is not supported currently

Pack (Activation type: All)
- Added rank 4d support for in[0] and 5d support for out[0]

CumulativeSum (Activation type: INT8)
- Added rank 5d support for in[0] and out [0]

HardSigmoid (Activation type: INT8, INT16)
- Added rank 5d support for in[0] and out [0]

Sigmoid, Softmax (Activation type: INT16)
- Added dynamic dimensions support on width and channel for in[0] and out[0]

ReduceMean (Activation type: INT16)
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0] and out[0]

ReduceSum (Activation type: FP16, FP32)
- Added rank 5d support for in[0] and out [0]

| | 2.26.0 | Quant |

RmsNorm
- Added QNN_DATATYPE_UFIXED_POINT_8 datatype support for in[0], in[1], in[2] and out[0]

UnPack
- Added rank 5d support for in[0]

Conv2d, TransposeConv2d, Convert
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0] and out[0]

MaMul
- Added rank 5d support for in[0], in[1] and out[0]

ElementWiseSelect
- Added rank 5d support for in[0], in[1], in[2] and out[0]

Pad
- Enabled EDGE scheme (QNN_OP_PAD_SCHEME_EDGE) to scheme parameter for FP16 and FP32

Transpose
- Added constraint that dynamic dimensions are not supported for in[0] and out[0]
- Added QNN_DATATYPE_BOOL_8 datatype support for in[0] to Transpose 5d

Tile
- Added QNN_DATATYPE_BOOL_8 datatype support for in[0] and out[0]

Softmax
- Added constraint that dynamic dimensions are not supported for in[0] and out[0]

| | 2.25.0 | Quant |

Gather
- Added constraint that input/output quant info must match for quantized models

GatherElements
- Added QNN_DATATYPE_INT_32 datatype support for in[1]

ElementWiseMultiply, ElementWiseAdd, ElementWiseSub, ElementWisePow
- Added rank 5d support for in[0], in[1] and out[0]
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for ElementWiseAdd,
  ElementWiseMultiply

ElementwiseRsqrt
- Added rank 5d support for in[0] and out[0] to both float and quant Rsqrt

TopK
- Added “largest” parameter and only support default value (true) currently

Relu
- Added support to updateable quantization for in[0]

Conv2d, Matmul, FullyConnected
- Added support to block quant weight tensors on V79 devices with the constraint that
  the block axis should be the second last axis of the weights

Prelu
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0], in[1] and out[0]

ResizeBilinear
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0] and out[0]

PoolMax2d
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0] and out[0]

ExtractPatches
- Added QNN_DATATYPE_FLOAT_16 datatype support for in[0] and out[0]

| | 2.24.0 | Quant |

HTP Backend Op Definition Supplement has been updated to enhance clarity on each
supported datatype combination. Please refer
to OpDef/HtpOpDefSupplement:HTP Backend Op Definition Supplement for details.

Reshape
- Added constraint that HTP currently does not support dynamic input/output

| | 2.23.0 | Quant |

Cast
- Added QNN_DATATYPE_INT_64 datatype support for in[0] and out[0]

Transpose
- Added QNN_DATATYPE_BOOL_8 datatype support for in[0]

Relu
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0] and out[0]

Gelu
- Added QNN_DATATYPE_SFIXED_POINT_8 datatype support for in[0] and out[0]

ElementwiseUnary
- Added rank 5d support to Abs op for in[0] and out[0]
- Added QNN_DATATYPE_SFIXED_POINT_8 datatype support to Abs op for in[0] and out[0]

| | 2.22.0 | Quant |

ElementwiseUnary
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0] and out[0] in RSQRT op

Conv3d, TransposeConv3d
- Added QNN_QUANTIZATION_ENCODING_AXIS_SCALE_OFFSET support with only
  channel axis and the weights are expected to be signed and symmetrically quantized

Reshape
- Added constraint that 0D tensors are not supported for in[0] and out[0]

ElementWiseAdd, ElementWiseAnd, ElementWiseDivide, ElementWiseNotEqual,
ElementWiseMaximum, ElementWiseMinimum, ElementWiseMultiply, ElementWisePower,
ElementWiseSquaredDifference, ElementWiseSubtract, ElementWiseEqual, ElementWiseGreater,
ElementWiseGreaterEqual, ElementWiseLess, ElementWiseLessEqual, ElementWiseBinary,
ElementWiseFloorDiv
- Added constraint that 0D tensors are not supported for inputs and outputs

ElementWiseAbs
- Added QNN_DATATYPE_SFIXED_POINT_8 datatype support for in[0] and out[0]

TopK
- Removed the constraint that for UFIXED_POINT_16 inputs, only k less than or equal to 64
  is supported

Transpose
- Added constraint for in[0] of Tranpose 4D: QNN_DATATYPE_UFIXED_POINT_8,
  QNN_DATATYPE_SFIXED_POINT_8, QNN_DATATYPE_UFIXED_POINT_16,
  QNN_DATATYPE_SFIXED_POINT_16, QNN_DATATYPE_INT_32, QNN_DATATYPE_UINT_32 are supported
- Added constraint for in[0] of Transpose 5D: QNN_DATATYPE_UFIXED_POINT_8,
  QNN_DATATYPE_SFIXED_POINT_8, QNN_DATATYPE_UFIXED_POINT_16, QNN_DATATYPE_FLOAT_16,
  QNN_DATATYPE_FLOAT_32 are supported

| | 2.21.0 | Quant |

Dequantize
- Added QNN_DATATYPE_FLOAT_16 datatype support for out[0]

ElementWiseBinary
- Added QNN_DATATYPE_BOOL_8 support for all ElementWiseBinary:comparison ops for in[0]
- Added QNN_DATATYPE_BOOL_8 support for all ElementWiseBinary:comparison ops for out[0]

| | 2.20.0 | Quant |

ElementWiseXor, CreateSparse, GetSparseIndices, GetSparseValues, SparseToDense,
ElementWiseNeuron
- Added support

ElementWiseSin, ElementWiseCos
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0], out[0]

Conv3d
- Added default handling to ignore reuse_sparse_indicies parameter
  as HTP doesn’t support sparsity

Resize
- Fixed constraint on nearest_mode parameter to match the behaviour in HTP core

Convert
- Added QNN_DATATYPE_UINT_8 datatype support for in[0]
- Added QNN_DATATYPE_BOOL_8 datatype support for out[0]

| | 2.19.0 | Quant |

Gather
- Added constraint to comunicate that HTP does not support negative indices

GatherElements
- Added QNN_DATATYPE_INT_32 support for in[0], out[0]

BatchNorm, LayerNorm
- Added constraint to support 16 bit data types for v73 or beyond architecture only

Convert
- Added max supported rank to 5d for in[0] and out[0]

| | 2.18.0 | Quant |

Conv2d, DepthWiseConv2d, TransposeConv2d, FullyConnected, MatMul
- Added constraint to support 16 bit data types for v73 or beyond architecture only

GridSample
- Added max supported rank to 5d for in[0], in[1] and out[0]

Lstm
- Added rest input for in[24]
- Added input rank constraint of 2 for in[0]
- Added description of 2d input not applicable for time_major parameter

| | 2.17.0 | Quant |

Quantize, Dequantize
- Added max supported rank to 5d for in[0] and out[0]

EltwiseMul
- Added overflow detect for input scales

| | 2.16.0 | Quant |

Matmul
- Corrected supported rank constraints back to 4D

Resize
- Added constraint to match nearest_mode only supporting default value

ElementwiseOr support added

ElementWiseBinary
- Enabled OR
- Added QNN_DATATYPE_BOOL_8 support for in[0], in[1], out[0]

| | 2.15.0 | Quant |

Split, ReduceMax, ReduceMean, ReduceMin, Convert, ElementWiseAbs
- Added 5D constraints for inputs and outputs

ElementWiseBinary support added

Convert
- Added QNN_DATATYPE_SFIXED_POINT_16 support for out[0]

Tile
- Added QNN_DATATYPE_FLOAT_32, QNN_DATATYPE_INT_32 support for input and output

Batchnorm
- Added QNN_DATATYPE_SFIXED_POINT_16 support for in[0] and in[1]
- Added QNN_DATATYPE_UFIXED_POINT_16 support for in[1]

Conv2d, DepthWiseConv2d, TransposeConv2
- Added QNN_DATATYPE_UFIXED_POINT_16 support for in[1]

ScatterNd
- Added QNN_DATATYPE_BOOL_8 support for in[0], in[2] and out[2]

| | 2.14.0 | Quant |

SpaceToDepth
- Added operations, enabled QNN_DATATYPE_UINT_32 mode

ReduceSum
- Added 5D constraints for inputs and outputs

LayerNorm
- Added QNN_DATATYPE_SFIXED_POINT_16 support for in[1] and in[2]

ElementWiseSquaredDifference
- Added QNN_DATATYPE_UFIXED_POINT_16, QNN_DATATYPE_SFIXED_POINT_16 support for
  in[0], in[1] and out[0]

FullyConnected, MatMul
- Added QNN_DATATYPE_UFIXED_POINT_16 support for in[1]

ElementWiseRsqrt
- Added QNN_DATATYPE_UFIXED_POINT_16 support for in[0] and out[0]

| | 2.13.0 | Quant |

Convert
- Added QNN_DATATYPE_BOOL_8 support for inputs

GroupNorm support added

ElementWiseRsqrt
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0] and out[0]

| | 2.12.0 | Quant |

ElementwiseUnary support added

Conv2d, DepthWiseConv2d, FullyConnected, MatMul, TransposeConv2d
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[0]
- Constraint added for in[1]: QNN_DATATYPE_SFIXED_POINT_16 Weight must have
  QNN_DATATYPE_UFIXED_POINT_16 Activation and must be symmetric quantized

RoiAlign
- Added default support for new params: aligned and allow_invalid_roi

| | 2.11.0 | Quant |

ElementWiseAsin, ExtractPatches, RoiAlign
- Added operations

Resize
- Removed transformation_mode parameter constraint to support Asymmetric Resize Mode

NonMaxSuppression
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0] and in[1]

DetectionOutput, MultiClassNms
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for all inputs and out[0]

| | 2.10.0 | Quant |

ElementWiseSin, ElementWiseCos, NonMaxSuppression
- Added operations

Conv2d, DepthWiseConv2d, FullyConnected, MatMul, TransposeConv2d
- Added QNN_DATATYPE_SFIXED_POINT_16 datatype support for in[1]

TopK
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0] and out[0]

Transpose
- Added QNN_DATATYPE_BOOL_8 datatype support for in[0] and out[0]

Fully-connected, MatMul
- Fixed Axis quantization validation

Conv2d, DepthWiseConv2d, FullyConnected, MatMul, TransposeConv2d
- Removed static tensor check on INT8 axis quantized weights for in[1]

Conv2d, DepthWiseConv2d, TransposeConv2d
- Allowed Non-Zero Bias Encoding with Per-Channel quantization parameters for in[2]

| | 2.9.0 | Quant |

L2Norm, LogSoftmax
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for in[0] and out[0]

ElementWiseEqual, ElementWiseGreater, ElementWiseGreaterEqual, ElementWiseLess
ElementWiseLessEqual, ElementWiseNotEqual
- Added QNN_DATATYPE_UFIXED_POINT_16 and QNN_DATATYPE_SFIXED_POINT_16 datatype support
  for in[0] and in[1]

Conv2d, DepthWiseConv2d, FullyConnected, MatMul, TransposeConv2d
- Added static tensor constraint for in[1]

MatMul
- Added channel axis constraint for quantization parameters for in[1]

ElementWiseAdd, ElementWiseDivide, ElementWiseMaximum, ElementWiseMinimum,
ElementWiseMultiply, ElementWiseSquaredDifference, ElementWiseSubtract, ElementWiseEqual,
ElementWiseGreater, ElementWiseGreaterEqual, ElementWiseLess, ElementWiseLessEqual,
ElementWiseNotEqual, ElementWiseSelect, Gather, GatherNd, MatMul, ScatterNd
- Fixed rank constraint on incorrect input for in[1]

ElementWiseSelect, ScatterNd
- Fixed rank constraint on incorrect input for in[2]

ElementWisePower, ExpandDims
- Added 5D rank constraint for in[1]

OneHot
- Added max rank constraint of 2 for in[0] and 3 for out[0]

ReluMinMax
- Added max rank constraint of 5 for in[0] and out[0]

| | 2.8.0 | Quant |

Cast, ElementWiseLog
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for inputs and outputs

ElementWiseGreaterEqual, ElementWiseLessEqual, ElementWiseNotEqual
- Added QNN_DATATYPE_INT_32 datatype support for inputs

ReduceSum, TopK
- Added QNN_DATATYPE_INT_32 datatype support for inputs and outputs

ElementWiseGreater, ElementWiseGreaterEqual, ElementWiseLess, ElementWiseLessEqual,
ElementWiseNotEqual, ElementWisePower, ElementWiseSelect, GatherNd, Softmax
- Added 5D constraints for inputs and outputs

ElementWiseSelect
- Added QNN_DATATYPE_UFIXED_POINT_8, QNN_DATATYPE_SFIXED_POINT_8,
  QNN_DATATYPE_SFIXED_POINT_16, QNN_DATATYPE_UFIXED_POINT_16, QNN_DATATYPE_INT_32
  datatype support for in[1]

| | 2.7.0 | Quant |

Argmax
- Added QNN_DATATYPE_UINT_32 datatype support for out[0]

Transpose
- Added QNN_DATATYPE_UINT_32 datatype support for in[0] and out[0]

DepthWiseConv2d
- Added support for dilation parameter with additional stride and kernel size

ElementWiseAdd, ElementWiseDivide, ElementWiseExp, ElementWiseMaximum,
ElementWiseMinimum, ElementWiseMultiply, ElementWiseSquaredDifference,
ElementWiseSubtract, MatMul, Pad, Relu, Sigmoid, Transpose
- Fixed 5D constraints for out[0]

ElementWiseExp, ElementWiseFloor, ReduceMax, ReduceMin, ScatterNd, LayerNorm
- Added QNN_DATATYPE_UFIXED_POINT_16 datatype support for all inputs and outputs

ElementWiseEqual, ElementWiseLess, ElementWiseSelect
- Added QNN_DATATYPE_INT_32 datatype support for all inputs and outputs

ElementWiseGreater
- Added QNN_DATATYPE_INT_32 datatype support for in[0] and in[1]

Reshape
- Added QNN_DATATYPE_BOOL_8 datatype support for in[0] and out[0]

ScatterNd
- Added 5D constraints for in[0], in[2] and out[0], and 6D constraint for in[1]

Softmax
- Added QNN_DATATYPE_FLOAT_32 datatype support for out[0]

InstanceNorm
- Added constraint to support in[0] with rank of less than 4D

Gather, GatherNd
- Added support for in[1]

GatherNd
- Added constraint for out[0] for input and output quantization check

FullyConnected, MatMul
- Added constraints to support per-channel tensors

| | 2.6.0 | Quant |

Cast
- Added QNN_DATATYPE_BOOL_8 datatype support for out[0]

| | 2.4.0 | Quant |

Resize support added

Gather
- Constraint added for in[0] and out[0]: “Max Supported rank is 5”

| | 2.3.0 | Quant |

Cast, ExpandDims, Squeeze
- Added QNN_DATATYPE_UINT_8 support for in[0] and out[0]

GatherNd
- Added QNN_DATATYPE_INT_32 support for in[0] and out[0]

MatMul
- Added QNN_DATATYPE_UFIXED_POINT_8 and QNN_DATATYPE_SFIXED_POINT_32 support for in[2]

Pad, Relu
- constraint added for in[0] and out[0]: “Max Supported rank is 5”

| | 2.2.0 | Quant |

Gelu
- Added QNN_DATATYPE_UFIXED_POINT_16 support for in[0] and out[0]

Reshape
- Added QNN_DATATYPE_UINT_8 support for in[0] and out[0]

| | 2.1.0 | Quant |

Concat, ElementWiseAdd, ElementWiseDivide, ElementWiseMaximum, ElementWiseMinimum,
ElementWiseMultiply, ElementWiseSubtract, ElementWiseSquaredDifference, MatMul,
Sigmoid, StridedSlice
- support for rank 5 added

Gather
- constraint added for out[0]: “Input quantization must be equal to output quantization”

| Last Published: Aug 06, 2026 [Previous Topic QNN HTA Op Definition Revision History](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/hta_opdef_version_history.md) [Next Topic QNN LPAI Op Definition Revision History](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/lpai_opdef_version_history.md)