AI Model Efficiency Toolkit
1.35.1
Getting Started
Installation
Install in Host Machine
Install in Docker Container
Quickstart Guide
Examples
Post-Training Quantization
Feature Descriptions
Adaptive Rounding (AdaRound)
AIMET PyTorch API
Quantized Modules
Quantizers
QuantizationMixin
quantization.affine
quantization.float
Encoding Analyzers
AI Model Efficiency Toolkit
Index
Index
_
|
A
|
C
|
D
|
E
|
F
|
G
|
I
|
M
|
O
|
P
|
Q
|
R
|
S
|
U
|
V
_
__quant_init__() (aimet_torch.v2.nn.QuantizationMixin method)
,
[1]
A
aimet_torch.v2.quantization.affine
module
aimet_torch.v2.quantization.float
module
allow_overwrite() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
apply_gptvq() (in module aimet_torch.gptvq.gptvq_weight.GPTVQ)
C
compute_encodings() (aimet_torch.v2.nn.QuantizationMixin method)
,
[1]
(aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
(aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer method)
D
dequantize() (aimet_torch.v2.quantization.tensor.DequantizedTensor method)
(aimet_torch.v2.quantization.tensor.QuantizedTensor method)
(in module aimet_torch.v2.quantization.affine)
DequantizedTensor (class in aimet_torch.v2.quantization.tensor)
E
EncodingAnalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)
F
FloatQuantizeDequantize (class in aimet_torch.v2.quantization.float)
,
[1]
forward() (aimet_torch.v2.nn.QuantizationMixin method)
,
[1]
(aimet_torch.v2.quantization.affine.quantizer.Quantize method)
(aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize method)
from_module() (aimet_torch.v2.nn.QuantizationMixin class method)
G
get_default_kernel() (aimet_torch.v2.nn.QuantizationMixin class method)
get_encoding() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
get_kernel() (aimet_torch.v2.nn.QuantizationMixin method)
get_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
GPTVQParameters (class in aimet_torch.gptvq.defs)
I
implements() (aimet_torch.v2.nn.QuantizationMixin class method)
input_quantizers (aimet_torch.v2.nn.QuantizationMixin attribute)
,
[1]
is_initialized() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
M
MinMaxEncodingAnalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)
module
aimet_torch.v2.quantization.affine
aimet_torch.v2.quantization.float
O
output_quantizers (aimet_torch.v2.nn.QuantizationMixin attribute)
,
[1]
P
param_quantizers (aimet_torch.v2.nn.QuantizationMixin attribute)
,
[1]
PercentileEncodingAnalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)
Q
QuantizationMixin (class in aimet_torch.v2.nn)
,
[1]
Quantize (class in aimet_torch.v2.quantization.affine)
(class in aimet_torch.v2.quantization.affine.quantizer)
quantize() (aimet_torch.v2.quantization.tensor.DequantizedTensor method)
(aimet_torch.v2.quantization.tensor.QuantizedTensor method)
(in module aimet_torch.v2.quantization.affine)
quantize_dequantize() (in module aimet_torch.v2.quantization.affine)
quantized_repr() (aimet_torch.v2.quantization.tensor.DequantizedTensor method)
(aimet_torch.v2.quantization.tensor.QuantizedTensor method)
QuantizeDequantize (class in aimet_torch.v2.quantization.affine)
(class in aimet_torch.v2.quantization.affine.quantizer)
(class in aimet_torch.v2.quantization.float)
,
[1]
QuantizedTensor (class in aimet_torch.v2.quantization.tensor)
QuantizerBase (class in aimet_torch.v2.quantization.affine.quantizer)
R
register_quantization_parameter() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
reset_stats() (aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer method)
S
set_activation_quantizers_to_float() (in module aimet_torch.v2.quantsim.config_utils)
set_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)
set_default_kernel() (aimet_torch.v2.nn.QuantizationMixin class method)
set_grouped_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)
set_kernel() (aimet_torch.v2.nn.QuantizationMixin method)
set_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.QuantizerBase method)
SqnrEncodingAnalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)
U
update_stats() (aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer method)
V
visualize_stats() (in module aimet_torch.v2.visualization_tools)