Skip to content

Commit a9bf79c

Browse files
authored
PyTorch AWQ Weight-only 3x API Implementation (#1561)
Signed-off-by: Kaihui-intel <[email protected]>
1 parent ac717bc commit a9bf79c

26 files changed

+1489
-27
lines changed

neural_compressor/torch/__init__.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/__init__.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/habana_fp8/__init__.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/habana_fp8/fp8_quant.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/habana_fp8/modules.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/habana_fp8/observer.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.

neural_compressor/torch/algorithms/weight_only/__init__.py

+2-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Copyright (c) 2023 Intel Corporation
1+
# Copyright (c) 2024 Intel Corporation
22
#
33
# Licensed under the Apache License, Version 2.0 (the "License");
44
# you may not use this file except in compliance with the License.
@@ -14,5 +14,6 @@
1414

1515
from .rtn import rtn_quantize
1616
from .gptq import gptq_quantize
17+
from .awq import awq_quantize
1718
from .modules import WeightOnlyLinear
1819
from .utility import *

0 commit comments

Comments
 (0)