QuantizeLinear¶
QuantizeLinear - 25¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
25function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 25.
Summary¶
The linear quantization operator consumes a high-precision tensor, a scale, and a zero point to compute the
low-precision/quantized tensor. The scale factor and zero point must have the same shape, determining the quantization
granularity. The quantization formula is y = saturate((x / y_scale) + y_zero_point).
Saturation is done according to:
uint16: [0, 65535]
int16: [-32768, 32767]
uint8: [0, 255]
int8: [-128, 127]
uint4: [0, 15]
int4: [-8, 7]
uint2: [0, 3]
int2: [-2, 1]
For (x / y_scale), it rounds to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details.
y_zero_point and y must have the same type. y_zero_point is usually not used for quantization to float8 and 4bit types, but the quantization
formula remains the same for consistency, and the type of the attribute y_zero_point still determines the quantization type.
x and y_scale are allowed to have different types. The type of y_scale determines the precision of the division operation between x and
y_scale, unless the precision attribute is specified.
There are three supported quantization granularities, determined by the shape of y_scale.
In all cases, y_zero_point must have the same shape as y_scale.
Per-tensor (per-layer) quantization:
y_scaleis a scalar.Per-axis quantization: The scale must be a 1-D tensor, with the length of the quantization axis. For an input shape
(D0, ..., Di, ..., Dn)andaxis=i,y_scaleis a 1-D tensor of lengthDi.Blocked quantization: The scale’s shape is identical to the input’s shape, except for one dimension, in which blocking is performed. Given
xshape(D0, ..., Di, ..., Dn),axis=i, and block sizeB:y_scaleshape is(D0, ..., ceil(Di/B), ..., Dn).
Attributes¶
axis - INT (default is
1):(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is
[-r, r-1]wherer = rank(input). When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.block_size - INT (default is
0):(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given
xshape(D0, ..., Di, ..., Dn),y_scaleshape(S0, ... Si, ...Sn)andaxis=i, the accepted range is[ceil(Di/Si), ceil(Di/(Si-1))-1]output_dtype - INT (default is
0):(Optional) The output data type. If not supplied, the output data type is inferred from
y_zero_pointdata type (T3). If neitheroutput_dtypenory_zero_pointare supplied, output data type is uint8. If bothoutput_dtypeandy_zero_pointare specified,output_dtypemust beT3.precision - INT (default is
0):(Optional) The precision of the division operation between
xandy_scale. If not provided, it will be the same as the type ofy_scale.saturate - INT (default is
1):The parameter defines how the conversion behaves if an input value is out of range of the destination type. It only applies for float 8 quantization (float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz). It is true by default. All cases are fully described in two tables inserted in the operator description.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - T2:
Scale for doing quantization to get
y. For per-tensor/layer quantization the scale is a scalar, for per-axis quantization it is a 1-D Tensor and for blocked quantization it has the same shape as the input, except for one dimension in which blocking is performed.y_zero_point (optional, heterogeneous) - T3:
Zero point for doing quantization to get
y. Shape must matchy_scale. Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T3:
N-D quantized output tensor. It has same shape as input
x.
Type Constraints¶
T1 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):The type of the input ‘x’.
T2 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(float8e8m0),tensor(int32)):The type of the input ‘y_scale’.
T3 in (
tensor(float4e2m1),tensor(float8e4m3fn),tensor(float8e4m3fnuz),tensor(float8e5m2),tensor(float8e5m2fnuz),tensor(int16),tensor(int2),tensor(int4),tensor(int8),tensor(uint16),tensor(uint2),tensor(uint4),tensor(uint8)):The type of the input
y_zero_pointand the outputy.
Examples¶
default¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array([0, 2, 3, 1000, -254, -1000]).astype(np.float32)
y_scale = np.float32(2)
y_zero_point = np.uint8(128)
y = np.array([128, 129, 130, 255, 1, 0]).astype(np.uint8)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear",
)
_axis¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array(
[
[
[[-162, 10], [-100, 232], [-20, -50]],
[[-76, 0], [0, 252], [32, -44]],
[[245, -485], [-960, -270], [-375, -470]],
],
],
dtype=np.float32,
)
y_scale = np.array([2, 4, 5], dtype=np.float32)
y_zero_point = np.array([84, 24, 196], dtype=np.uint8)
y = (x / y_scale.reshape(1, 3, 1, 1) + y_zero_point.reshape(1, 3, 1, 1)).astype(
np.uint8
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_axis",
)
_e4m3fn¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array([0.0, 1.0, 2.0, 100000.0, 200.0]).astype(np.float32)
y_scale = np.float32(2)
y_zero_point = make_tensor("y_zero_point", TensorProto.FLOAT8E4M3FN, [1], [0])
y = make_tensor("y", TensorProto.FLOAT8E4M3FN, [5], [0, 0.5, 1, 448, 96])
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_e4m3fn",
)
_e5m2¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array([0.0, 1.0, 2.0, 100000.0, 200.0]).astype(np.float32)
y_scale = np.float32(2)
y_zero_point = make_tensor("y_zero_point", TensorProto.FLOAT8E5M2, [1], [0.0])
y = make_tensor("y", TensorProto.FLOAT8E5M2, [5], [0, 0.5, 1, 49152, 96])
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_e5m2",
)
_uint16¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array(
[
0.0,
-128.0,
3.0,
-3.0,
2.9,
-2.9,
3.1,
-3.1,
65536.0,
-65534.0,
70000.0,
-70000.0,
]
).astype(np.float32)
y_scale = np.float32(2.0)
y_zero_point = np.uint16(32767)
y = np.array(
[
32767,
32703,
32769,
32765,
32768,
32766,
32769,
32765,
65535,
0,
65535,
0,
]
).astype(np.uint16)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_uint16",
)
_int16¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
)
x = np.array(
[
0.0,
-514.0,
3.0,
-3.0,
2.9,
-2.9,
3.1,
-3.1,
65022.0,
-66046.0,
65023.0,
-66047.0,
65024.0,
-66048.0,
70000.0,
-70000.0,
]
).astype(np.float32)
y_scale = np.float32(2.0)
y_zero_point = np.int16(256)
y = np.array(
[
256,
-1,
258,
254,
257,
255,
258,
254,
32767,
-32767,
32767,
-32768,
32767,
-32768,
32767,
-32768,
]
).astype(np.int16)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_int16",
)
_uint4¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=0,
)
x = np.array(
[
[0.0, 2.5, 4.8, 8.6],
[-30, -20, 6, 9],
[12, 15, 16, 40],
]
).astype(np.float32)
y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
y_zero_point = make_tensor(
"y_zero_point", TensorProto.UINT4, y_scale.shape, np.ones_like(y_scale)
)
y = make_tensor(
"y", TensorProto.UINT4, x.shape, [1, 2, 3, 5, 0, 0, 3, 4, 4, 5, 5, 11]
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_uint4",
)
_int4¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=0,
)
x = np.array(
[
[0.0, 2.5, 4.8, 8.6],
[-30, -20, 6, 9],
[12, 15, 16, 40],
]
).astype(np.float32)
y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
y_zero_point = make_tensor(
"y_zero_point", TensorProto.INT4, y_scale.shape, np.ones_like(y_scale)
)
y = make_tensor(
"y", TensorProto.INT4, x.shape, [1, 2, 3, 5, -8, -6, 3, 4, 4, 5, 5, 7]
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_int4",
)
_uint2¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=0,
)
x = np.array(
[
[0.0, 2.5, 4.8, 8.6],
[-2.0, -1.0, 1.0, 3.0],
[4.0, 5.0, 6.0, 7.0],
],
dtype=np.float32,
)
y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
y_zero_point = make_tensor(
"y_zero_point", TensorProto.UINT2, y_scale.shape, np.zeros_like(y_scale)
)
y = make_tensor(
"y", TensorProto.UINT2, x.shape, [0, 1, 2, 3, 0, 0, 0, 1, 1, 1, 2, 2]
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_uint2",
)
_int2¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=0,
)
x = np.array(
[
[0.0, 2.5, 4.8, 8.6],
[-4.0, -3.0, 1.0, 2.0],
[-0.0, -2.5, -4.8, -8.6],
],
dtype=np.float32,
)
y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
y_zero_point = make_tensor(
"y_zero_point", TensorProto.INT2, y_scale.shape, np.zeros_like(y_scale)
)
y = make_tensor(
"y", TensorProto.INT2, x.shape, [0, 1, 1, 1, -1, -1, 0, 1, 0, -1, -1, -2]
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_int2",
)
_float4e2m1¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=0,
)
x = np.array(
[
[0.0, 2.5, 4.8, 8.6],
[-30, -20, 6, 9],
[-0.0, -2.5, -4.8, -8.6],
]
).astype(np.float32)
y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
y_zero_point = make_tensor(
"y_zero_point",
TensorProto.FLOAT4E2M1,
y_scale.shape,
np.zeros_like(y_scale),
)
y = make_tensor(
"y",
TensorProto.FLOAT4E2M1,
x.shape,
[0, 1, 2, 4, -6, -6, 2, 3, 0, -0.5, -1, -2],
)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_float4e2m1",
)
_blocked_asymmetric¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale", "y_zero_point"],
outputs=["y"],
axis=1,
block_size=2,
)
x = np.array(
[
[6.0, 12.0, 50.0, 5.0],
[1.0, 8.0, 4.0, 5.0],
[0.0, 20.0, 10.0, 4.0],
],
dtype=np.float32,
)
y_scale = np.array(
[
[1.5, 2.5],
[3.0, 4.9],
[5.1, 6.9],
],
dtype=np.float32,
)
y_zero_point = np.array(
[
[0, 1],
[1, 0],
[2, 3],
],
dtype=np.uint8,
)
# x.shape = (3, 4)
# y_scale.shape = (3, 2)
assert y_scale.shape == y_zero_point.shape
block_axis = 1
# The block shape is [x.shape[i] // y_scale.shape[i] for i in range(len(x.shape))] = (1, 2)
assert all(
x.shape[i] == y_scale.shape[i]
for i in range(len(x.shape))
if i != block_axis
)
assert x.shape[block_axis] % y_scale.shape[block_axis] == 0
repeats = x.shape[block_axis] // y_scale.shape[block_axis]
# Create element-wise scale and zero point
y_scale_elementwise = np.repeat(y_scale, repeats=repeats, axis=block_axis)
y_zero_point_elementwise = np.repeat(
y_zero_point, repeats=repeats, axis=block_axis
)
y = np.rint(x / y_scale_elementwise + y_zero_point_elementwise).astype(np.uint8)
expect(
node,
inputs=[x, y_scale, y_zero_point],
outputs=[y],
name="test_quantizelinear_blocked_asymmetric",
)
_blocked_symmetric¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"QuantizeLinear",
inputs=["x", "y_scale"],
outputs=["y"],
axis=1,
block_size=2,
output_dtype=TensorProto.INT16,
)
x = np.array(
[
[6.0, -8, -10, 5.0],
[1.0, 8.0, 4.0, 5.0],
[0.0, 20.0, 10.0, 4.0],
],
dtype=np.float32,
)
y_scale = np.array(
[
[1.5, 2.5],
[3.0, 4.9],
[5.1, 6.9],
],
dtype=np.float32,
)
# x.shape = (3, 4)
# y_scale.shape = (3, 2)
block_axis = 1
# The block shape is [x.shape[i] // y_scale.shape[i] for i in range(len(x.shape))] = (1, 2)
assert all(
x.shape[i] == y_scale.shape[i]
for i in range(len(x.shape))
if i != block_axis
)
assert x.shape[block_axis] % y_scale.shape[block_axis] == 0
repeats = x.shape[block_axis] // y_scale.shape[block_axis]
# Create element-wise scale and zero point
y_scale_elementwise = np.repeat(y_scale, repeats=repeats, axis=block_axis)
y_val = np.clip(
np.rint(x / y_scale_elementwise), a_min=-32768, a_max=32767
).astype(np.int16)
y = make_tensor(
"y",
TensorProto.INT16,
x.shape,
y_val,
)
expect(
node,
inputs=[x, y_scale],
outputs=[y],
name="test_quantizelinear_blocked_symmetric",
)
QuantizeLinear - 24¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
24function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 24.
Summary¶
The linear quantization operator consumes a high-precision tensor, a scale, and a zero point to compute the
low-precision/quantized tensor. The scale factor and zero point must have the same shape, determining the quantization
granularity. The quantization formula is y = saturate((x / y_scale) + y_zero_point).
Saturation is done according to:
uint16: [0, 65535]
int16: [-32768, 32767]
uint8: [0, 255]
int8: [-128, 127]
uint4: [0, 15]
int4: [-8, 7]
For (x / y_scale), it rounds to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details.
y_zero_point and y must have the same type. y_zero_point is usually not used for quantization to float8 and 4bit types, but the quantization
formula remains the same for consistency, and the type of the attribute y_zero_point still determines the quantization type.
x and y_scale are allowed to have different types. The type of y_scale determines the precision of the division operation between x and
y_scale, unless the precision attribute is specified.
There are three supported quantization granularities, determined by the shape of y_scale.
In all cases, y_zero_point must have the same shape as y_scale.
Per-tensor (per-layer) quantization:
y_scaleis a scalar.Per-axis quantization: The scale must be a 1-D tensor, with the length of the quantization axis. For an input shape
(D0, ..., Di, ..., Dn)andaxis=i,y_scaleis a 1-D tensor of lengthDi.Blocked quantization: The scale’s shape is identical to the input’s shape, except for one dimension, in which blocking is performed. Given
xshape(D0, ..., Di, ..., Dn),axis=i, and block sizeB:y_scaleshape is(D0, ..., ceil(Di/B), ..., Dn).
Attributes¶
axis - INT (default is
1):(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is
[-r, r-1]wherer = rank(input). When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.block_size - INT (default is
0):(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given
xshape(D0, ..., Di, ..., Dn),y_scaleshape(S0, ... Si, ...Sn)andaxis=i, the accepted range is[ceil(Di/Si), ceil(Di/(Si-1))-1]output_dtype - INT (default is
0):(Optional) The output data type. If not supplied, the output data type is inferred from
y_zero_pointdata type (T3). If neitheroutput_dtypenory_zero_pointare supplied, output data type is uint8. If bothoutput_dtypeandy_zero_pointare specified,output_dtypemust beT3.precision - INT (default is
0):(Optional) The precision of the division operation between
xandy_scale. If not provided, it will be the same as the type ofy_scale.saturate - INT (default is
1):The parameter defines how the conversion behaves if an input value is out of range of the destination type. It only applies for float 8 quantization (float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz). It is true by default. All cases are fully described in two tables inserted in the operator description.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - T2:
Scale for doing quantization to get
y. For per-tensor/layer quantization the scale is a scalar, for per-axis quantization it is a 1-D Tensor and for blocked quantization it has the same shape as the input, except for one dimension in which blocking is performed.y_zero_point (optional, heterogeneous) - T3:
Zero point for doing quantization to get
y. Shape must matchy_scale. Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T3:
N-D quantized output tensor. It has same shape as input
x.
Type Constraints¶
T1 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):The type of the input ‘x’.
T2 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(float8e8m0),tensor(int32)):The type of the input ‘y_scale’.
T3 in (
tensor(float4e2m1),tensor(float8e4m3fn),tensor(float8e4m3fnuz),tensor(float8e5m2),tensor(float8e5m2fnuz),tensor(int16),tensor(int4),tensor(int8),tensor(uint16),tensor(uint4),tensor(uint8)):The type of the input
y_zero_pointand the outputy.
QuantizeLinear - 23¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
23function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 23.
Summary¶
The linear quantization operator consumes a high-precision tensor, a scale, and a zero point to compute the
low-precision/quantized tensor. The scale factor and zero point must have the same shape, determining the quantization
granularity. The quantization formula is y = saturate((x / y_scale) + y_zero_point).
Saturation is done according to:
uint16: [0, 65535]
int16: [-32768, 32767]
uint8: [0, 255]
int8: [-128, 127]
uint4: [0, 15]
int4: [-8, 7]
For (x / y_scale), it rounds to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details.
y_zero_point and y must have the same type. y_zero_point is usually not used for quantization to float8 and 4bit types, but the quantization
formula remains the same for consistency, and the type of the attribute y_zero_point still determines the quantization type.
x and y_scale are allowed to have different types. The type of y_scale determines the precision of the division operation between x and
y_scale, unless the precision attribute is specified.
There are three supported quantization granularities, determined by the shape of y_scale.
In all cases, y_zero_point must have the same shape as y_scale.
Per-tensor (per-layer) quantization:
y_scaleis a scalar.Per-axis quantization: The scale must be a 1-D tensor, with the length of the quantization axis. For an input shape
(D0, ..., Di, ..., Dn)andaxis=i,y_scaleis a 1-D tensor of lengthDi.Blocked quantization: The scale’s shape is identical to the input’s shape, except for one dimension, in which blocking is performed. Given
xshape(D0, ..., Di, ..., Dn),axis=i, and block sizeB:y_scaleshape is(D0, ..., ceil(Di/B), ..., Dn).
Attributes¶
axis - INT (default is
1):(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is
[-r, r-1]wherer = rank(input). When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.block_size - INT (default is
0):(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given
xshape(D0, ..., Di, ..., Dn),y_scaleshape(S0, ... Si, ...Sn)andaxis=i, the accepted range is[ceil(Di/Si), ceil(Di/(Si-1))-1]output_dtype - INT (default is
0):(Optional) The output data type. If not supplied, the output data type is inferred from
y_zero_pointdata type (T3). If neitheroutput_dtypenory_zero_pointare supplied, output data type is uint8. If bothoutput_dtypeandy_zero_pointare specified,output_dtypemust beT3.precision - INT (default is
0):(Optional) The precision of the division operation between
xandy_scale. If not provided, it will be the same as the type ofy_scale.saturate - INT (default is
1):The parameter defines how the conversion behaves if an input value is out of range of the destination type. It only applies for float 8 quantization (float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz). It is true by default. All cases are fully described in two tables inserted in the operator description.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - T2:
Scale for doing quantization to get
y. For per-tensor/layer quantization the scale is a scalar, for per-axis quantization it is a 1-D Tensor and for blocked quantization it has the same shape as the input, except for one dimension in which blocking is performed.y_zero_point (optional, heterogeneous) - T3:
Zero point for doing quantization to get
y. Shape must matchy_scale.Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T3:
N-D quantized output tensor. It has same shape as input
x.
Type Constraints¶
T1 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):The type of the input ‘x’.
T2 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):The type of the input ‘y_scale’.
T3 in (
tensor(float4e2m1),tensor(float8e4m3fn),tensor(float8e4m3fnuz),tensor(float8e5m2),tensor(float8e5m2fnuz),tensor(int16),tensor(int4),tensor(int8),tensor(uint16),tensor(uint4),tensor(uint8)):The type of the input
y_zero_pointand the outputy.
QuantizeLinear - 21¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
21function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 21.
Summary¶
The linear quantization operator consumes a high-precision tensor, a scale, and a zero point to compute the
low-precision/quantized tensor. The scale factor and zero point must have the same shape, determining the quantization
granularity. The quantization formula is y = saturate((x / y_scale) + y_zero_point).
Saturation is done according to:
uint16: [0, 65535]
int16: [-32768, 32767]
uint8: [0, 255]
int8: [-128, 127]
uint4: [0, 15]
int4: [-8, 7] For
(x / y_scale), it rounds to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details.y_zero_pointandymust have the same type.y_zero_pointis usually not used for quantization to float8 types, but the quantization formula remains the same for consistency, and the type of the attributey_zero_pointstill determines the quantization type. There are three supported quantization granularities, determined by the shape ofy_scale. In all cases,y_zero_pointmust have the same shape asy_scale.Per-tensor (per-layer) quantization:
y_scaleis a scalar.Per-axis quantization: The scale must be a 1-D tensor, with the length of the quantization axis. For an input shape
(D0, ..., Di, ..., Dn)andaxis=i,y_scaleis a 1-D tensor of lengthDi.Blocked quantization: The scale’s shape is identical to the input’s shape, except for one dimension, in which blocking is performed. Given
xshape(D0, ..., Di, ..., Dn),axis=i, and block sizeB:y_scaleshape is(D0, ..., ceil(Di/B), ..., Dn).
Attributes¶
axis - INT (default is
1):(Optional) The axis of the dequantizing dimension of the input tensor. Used only for per-axis and blocked quantization. Negative value means counting dimensions from the back. Accepted range is
[-r, r-1]wherer = rank(input). When the rank of the input is 1, per-tensor quantization is applied, rendering the axis unnecessary in this scenario.block_size - INT (default is
0):(Optional) The size of the quantization block (number of times every scale is replicated). Used only for blocked quantization. The block size is a positive integer. Given
xshape(D0, ..., Di, ..., Dn),y_scaleshape(S0, ... Si, ...Sn)andaxis=i, the accepted range is[ceil(Di/Si), ceil(Di/(Si-1))-1]output_dtype - INT (default is
0):(Optional) The output data type. If not supplied, the output data type is inferred from
y_zero_pointdata type (T2). If neitheroutput_dtypenory_zero_pointare supplied, output data type is uint8. If bothoutput_dtypeandy_zero_pointare specified,output_dtypemust beT2.saturate - INT (default is
1):The parameter defines how the conversion behaves if an input value is out of range of the destination type. It only applies for float 8 quantization (float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz). It is true by default. All cases are fully described in two tables inserted in the operator description.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - T1:
Scale for doing quantization to get
y. For per-tensor/layer quantization the scale is a scalar, for per-axis quantization it is a 1-D Tensor and for blocked quantization it has the same shape as the input, except for one dimension in which blocking is performed.y_zero_point (optional, heterogeneous) - T2:
Zero point for doing quantization to get
y. Shape must matchy_scale.Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T2:
N-D quantized output tensor. It has same shape as input
x.
Type Constraints¶
T1 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):The type of the input ‘x’.
T2 in (
tensor(float8e4m3fn),tensor(float8e4m3fnuz),tensor(float8e5m2),tensor(float8e5m2fnuz),tensor(int16),tensor(int4),tensor(int8),tensor(uint16),tensor(uint4),tensor(uint8)):The type of the input
y_zero_pointand the outputy.
QuantizeLinear - 19¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
19function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 19.
Summary¶
The linear quantization operator. It consumes a high precision tensor, a scale, and a zero point to compute the low precision / quantized tensor.
The scale factor and zero point must have same shape, and can be either a scalar for per-tensor / per layer quantization, or a 1-D tensor for per-axis quantization.
The quantization formula is y = saturate ((x / y_scale) + y_zero_point).
For saturation, it saturates to [0, 255] if it’s uint8, or [-128, 127] if it’s int8.
For (x / y_scale), it’s rounding to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details.
‘y_zero_point’ and ‘y’ must have same type.
‘y_zero_point’ is usually not used for quantization to float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz,
but the quantization formula remains the same for consistency and
the type of the attribute ‘y_zero_point’ still determines the quantization type.
Attributes¶
axis - INT (default is
1):(Optional) The axis of the quantization dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input).
saturate - INT (default is
1):The parameter defines how the conversion behaves if an input value is out of range of the destination type. It only applies for float 8 quantization (float8e4m3fn, float8e4m3fnuz, float8e5m2, float8e5m2fnuz). It is true by default. All cases are fully described in two tables inserted in the operator description.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - T1:
Scale for doing quantization to get ‘y’. It can be a scalar, which means per-tensor/layer quantization, or a 1-D Tensor for per-axis quantization.
y_zero_point (optional, heterogeneous) - T2:
Zero point for doing quantization to get ‘y’. Shape must match y_scale. Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T2:
N-D quantized output tensor. It has same shape as input ‘x’.
Type Constraints¶
T1 in (
tensor(bfloat16),tensor(float),tensor(float16),tensor(int32)):Constrain ‘x’ to float, float16, bfloat16 or int32 tensor.
T2 in (
tensor(float8e4m3fn),tensor(float8e4m3fnuz),tensor(float8e5m2),tensor(float8e5m2fnuz),tensor(int8),tensor(uint8)):Constrain ‘y_zero_point’ and ‘y’ to 8-bit integer/float tensor.
QuantizeLinear - 13¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
13function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 13.
Summary¶
The linear quantization operator. It consumes a high precision tensor, a scale, and a zero point to compute the low precision / quantized tensor. The scale factor and zero point must have same shape, and can be either a scalar for per-tensor / per layer quantization, or a 1-D tensor for per-axis quantization. The quantization formula is y = saturate ((x / y_scale) + y_zero_point). For saturation, it saturates to [0, 255] if it’s uint8, or [-128, 127] if it’s int8. For (x / y_scale), it’s rounding to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details. ‘y_zero_point’ and ‘y’ must have same type.
Attributes¶
axis - INT (default is
1):(Optional) The axis of the quantization dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input).
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - tensor(float):
Scale for doing quantization to get ‘y’. It can be a scalar, which means per-tensor/layer quantization, or a 1-D Tensor for per-axis quantization.
y_zero_point (optional, heterogeneous) - T2:
Zero point for doing quantization to get ‘y’. Shape must match y_scale. Default is uint8 with zero point of 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T2:
N-D quantized output tensor. It has same shape as input ‘x’.
Type Constraints¶
T1 in (
tensor(float),tensor(int32)):Constrain ‘x’ to float or int32 tensor.
T2 in (
tensor(int8),tensor(uint8)):Constrain ‘y_zero_point’ and ‘y’ to 8-bit integer tensor.
QuantizeLinear - 10¶
Version¶
name: QuantizeLinear (GitHub)
domain:
mainsince_version:
10function:
Falsesupport_level:
SupportType.COMMONshape inference:
True
This version of the operator has been available since version 10.
Summary¶
The linear per-tensor/layer quantization operator. It consumes a high precision tensor, a scale, a zero point to compute the low precision / quantized tensor. The quantization formula is y = saturate ((x / y_scale) + y_zero_point). For saturation, it saturates to [0, 255] if it’s uint8, or [-128, 127] if it’s int8. For (x / y_scale), it’s rounding to the nearest even. Refer to https://en.wikipedia.org/wiki/Rounding for details. ‘y_zero_point’ and ‘y’ must have same type.
Inputs¶
Between 2 and 3 inputs.
x (heterogeneous) - T1:
N-D full precision Input tensor to be quantized.
y_scale (heterogeneous) - tensor(float):
Scale for doing quantization to get ‘y’. It’s a scalar, which means a per-tensor/layer quantization.
y_zero_point (optional, heterogeneous) - T2:
Zero point for doing quantization to get ‘y’. It’s a scalar, which means a per-tensor/layer quantization. Default value is uint8 typed 0 if it’s not specified.
Outputs¶
y (heterogeneous) - T2:
N-D quantized output tensor. It has same shape as input ‘x’.
Type Constraints¶
T1 in (
tensor(float),tensor(int32)):Constrain ‘x’ to float or int32 tensor.
T2 in (
tensor(int8),tensor(uint8)):Constrain ‘y_zero_point’ and ‘y’ to 8-bit integer tensor.