keras-nightly 3.12.0.dev2025090303__py3-none-any.whl → 3.12.0.dev2025090503__py3-none-any.whl

keras/src/version.py

@@ -1,7 +1,7 @@
 from keras.src.api_export import keras_export
 
 # Unique source of truth for the version number.
-__version__ = "3.12.0.dev2025090303"
+__version__ = "3.12.0.dev2025090503"
 
 
 @keras_export("keras.version")

{keras_nightly-3.12.0.dev2025090303.dist-info → keras_nightly-3.12.0.dev2025090503.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-nightly
-Version: 3.12.0.dev2025090303
+Version: 3.12.0.dev2025090503
 Summary: Multi-backend Keras
 Author-email: Keras team <keras-users@googlegroups.com>
 License: Apache License 2.0

{keras_nightly-3.12.0.dev2025090303.dist-info → keras_nightly-3.12.0.dev2025090503.dist-info}/RECORD

@@ -44,11 +44,11 @@ keras/_tf_keras/keras/losses/__init__.py,sha256=xBc_KOtSLwp3h3CKQ0EnCuIy-Bsak2SP
 keras/_tf_keras/keras/metrics/__init__.py,sha256=_wF31PTvua5ahF9JEW4Hx1UVNjVCLqVI8J5JNrZCBf8,6546
 keras/_tf_keras/keras/mixed_precision/__init__.py,sha256=AM51CzHqzcY75tqdpQiuVcTRUEpUzBqeb-EfLeSDSV8,727
 keras/_tf_keras/keras/models/__init__.py,sha256=83pyA0pzytqin8JLV6FEbPreCb-V64ToebxFGrHsVdQ,501
-keras/_tf_keras/keras/ops/__init__.py,sha256=yQXz8CrRtgdWsn8hAnqlj598WXteZ-z_-TfgDKxV_WA,14731
+keras/_tf_keras/keras/ops/__init__.py,sha256=xRJsr1GlVFl3FOzL-q80ZyKdc5p87EaphlALJIdR1SQ,14776
 keras/_tf_keras/keras/ops/image/__init__.py,sha256=K57F1fBruHn6hacx9uQFWPYO1qbdNM40VR3djvKIRq4,961
 keras/_tf_keras/keras/ops/linalg/__init__.py,sha256=cc8apE35y2X8idUxY-kc7qYCUm3SAvY2b_StSjRB7Ro,778
 keras/_tf_keras/keras/ops/nn/__init__.py,sha256=DAloStL366PAGID_tqeSKnConPl5aB4dcyNVm8bWnUU,2802
-keras/_tf_keras/keras/ops/numpy/__init__.py,sha256=PWk69Pi1Z8KLcK_ByDepAxBHvPfU5DL1vxXuvqkd3cU,9027
+keras/_tf_keras/keras/ops/numpy/__init__.py,sha256=3AL2NyuxFcski5t45CbatwY3VGa6hco-hvHcxW_WcQo,9072
 keras/_tf_keras/keras/optimizers/__init__.py,sha256=1fx0vEB-oGu-9dumxoIvX4qVHdgJvf74OLyYoBkE2y0,1267
 keras/_tf_keras/keras/optimizers/legacy/__init__.py,sha256=uIMQESCV80Q0FY-9ikQUjXYPyZqmTfAM3dfohQ5DzYs,516
 keras/_tf_keras/keras/optimizers/schedules/__init__.py,sha256=pQF3rQiAPuUSTUdflTr-fpL77oyGIv9xzGdjae3M3kw,1120
@@ -109,11 +109,11 @@ keras/losses/__init__.py,sha256=VIXBHQFNdLUPZ7JuwtIKj_4E-xf2yvNyrmdklvjr_xM,3667
 keras/metrics/__init__.py,sha256=qeEwtqpSCAaCr8BMUv1eVaqJl2Zb83OB5K0BG3JB0nI,6245
 keras/mixed_precision/__init__.py,sha256=AM51CzHqzcY75tqdpQiuVcTRUEpUzBqeb-EfLeSDSV8,727
 keras/models/__init__.py,sha256=83pyA0pzytqin8JLV6FEbPreCb-V64ToebxFGrHsVdQ,501
-keras/ops/__init__.py,sha256=yQXz8CrRtgdWsn8hAnqlj598WXteZ-z_-TfgDKxV_WA,14731
+keras/ops/__init__.py,sha256=xRJsr1GlVFl3FOzL-q80ZyKdc5p87EaphlALJIdR1SQ,14776
 keras/ops/image/__init__.py,sha256=K57F1fBruHn6hacx9uQFWPYO1qbdNM40VR3djvKIRq4,961
 keras/ops/linalg/__init__.py,sha256=cc8apE35y2X8idUxY-kc7qYCUm3SAvY2b_StSjRB7Ro,778
 keras/ops/nn/__init__.py,sha256=DAloStL366PAGID_tqeSKnConPl5aB4dcyNVm8bWnUU,2802
-keras/ops/numpy/__init__.py,sha256=PWk69Pi1Z8KLcK_ByDepAxBHvPfU5DL1vxXuvqkd3cU,9027
+keras/ops/numpy/__init__.py,sha256=3AL2NyuxFcski5t45CbatwY3VGa6hco-hvHcxW_WcQo,9072
 keras/optimizers/__init__.py,sha256=1fx0vEB-oGu-9dumxoIvX4qVHdgJvf74OLyYoBkE2y0,1267
 keras/optimizers/legacy/__init__.py,sha256=uIMQESCV80Q0FY-9ikQUjXYPyZqmTfAM3dfohQ5DzYs,516
 keras/optimizers/schedules/__init__.py,sha256=pQF3rQiAPuUSTUdflTr-fpL77oyGIv9xzGdjae3M3kw,1120
@@ -126,7 +126,7 @@ keras/regularizers/__init__.py,sha256=542Shphw7W8h4Dyf2rmqMKUECVZ8IVBvN9g1LWhz-b
 keras/saving/__init__.py,sha256=KvL2GZxjvgFgEhvEnkvqjIR9JSNHKz-NWZacXajsjLI,1298
 keras/src/__init__.py,sha256=Gi4S7EiCMkE03PbdGNpFdaUYySWDs_FcAJ8Taz9Y1BE,684
 keras/src/api_export.py,sha256=gXOkBOnmscV013WAc75lc4Up01-Kkg9EylIAT_QWctg,1173
-keras/src/version.py,sha256=10rfmpGBb6KJKrifewkNq8aWHatUOvbKV8SoOP3HJUw,204
+keras/src/version.py,sha256=f4wgAnvTNADitPmga3-jCHgq7Iz24bPZA31q1dURAJE,204
 keras/src/activations/__init__.py,sha256=0nL3IFDB9unlrMz8ninKOWo-uCHasTUpTo1tXZb2u44,4433
 keras/src/activations/activations.py,sha256=mogPggtp4CGldI3VOPNmesRxp6EbiR1_i4KLGaVwzL8,17614
 keras/src/applications/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -169,7 +169,7 @@ keras/src/backend/jax/layer.py,sha256=o6CicT06udwamTRQIjNSDLZLyYHFzBXNbxewXgWe0i
 keras/src/backend/jax/linalg.py,sha256=dtGHRYCvoVlRX0UwbDDdunA8Vp_mA3sdqoasX4P8SbQ,2532
 keras/src/backend/jax/math.py,sha256=1IEDpdoF8e5ltu3D4wbDQuihzvJHhMXz8W9Z_E-eJqU,9391
 keras/src/backend/jax/nn.py,sha256=R0a8-WB0YCl14FpRi2CQ45MFRvHCFtPTedk0Q1LfWYc,45935
-keras/src/backend/jax/numpy.py,sha256=S0FA9ZM0U9zYH_011-89xAoe_UCpMKeSTTskniBNAoE,36907
+keras/src/backend/jax/numpy.py,sha256=24u0ypCCjvlnpr0diBlGAP373XnzYNjFK3kuv9N_Oro,37017
 keras/src/backend/jax/optimizer.py,sha256=JSKRkBteb7u-He5rtHwU6Wy5p8IjSsZf-IIL4-eQfsE,4102
 keras/src/backend/jax/random.py,sha256=Uk2huGIk_dlzMrx5eDVrrr2TeCEMitn2vr4yzA0NXjs,3594
 keras/src/backend/jax/rnn.py,sha256=Ycq0qfLY4M4jhltvztpLQyywjEM17T7CZQFh4hhHOUE,7767
@@ -184,7 +184,7 @@ keras/src/backend/numpy/layer.py,sha256=dTk7W7ql7vRgll7JbOXK5PlIhQw5VHdpSjKciHd8
 keras/src/backend/numpy/linalg.py,sha256=H8Bdu8LG6OlzXqx8uVxLmTKKE8s9lMoZHMsM2tW4e04,2417
 keras/src/backend/numpy/math.py,sha256=HdkEA5ro7dtQBTP78GFIgqTFLgNQ49PXHhqI1vLRGfo,10169
 keras/src/backend/numpy/nn.py,sha256=wTh4s2ZvL4PjPjz4VE6tMrFkRMaQiqpdBeNb6RY5kyE,36623
-keras/src/backend/numpy/numpy.py,sha256=gr2kiDR9bbFFDOkM-q0h1Ke6o2b-GFS33Cw0Cab8cnk,35408
+keras/src/backend/numpy/numpy.py,sha256=KfzmeN5WO1u8lhZJSiewWO3psln7p9XL3Id-Zglijos,35582
 keras/src/backend/numpy/random.py,sha256=wx2nE75q7L2cBMjtQlQx8yKMj4Ie3puFMDQsbrZO8SA,3961
 keras/src/backend/numpy/rnn.py,sha256=thOsMung1qR3lQsR4_D6hqKMFollQgrB0KwsJLk4BMY,7867
 keras/src/backend/numpy/trainer.py,sha256=MzWr8_LLHa1P6fxdUWirGw_lQwHGF_vkZ7RUGLUzjUs,11126
@@ -196,7 +196,7 @@ keras/src/backend/openvino/layer.py,sha256=5RdvaH1yOyPAphjKiuQAK1H_yZFYKE1Hp7c5b
 keras/src/backend/openvino/linalg.py,sha256=Q09iv7fcE-xtNOop_hTG_RADkI0CHhjfrcOHqdWCmIY,1486
 keras/src/backend/openvino/math.py,sha256=qw9kX2sJ2qr0dBJF12Ey0E2GcwixPUqoev6UcNra4NI,3944
 keras/src/backend/openvino/nn.py,sha256=FUjNvBOcwP-A1BHffaCIZ-bl6na6xM_v91dcaTP4Q4U,15121
-keras/src/backend/openvino/numpy.py,sha256=XYXmWh7i-3jsPq0Dpzw8bwcspgKUoIzKa1_wa_EX5fg,65713
+keras/src/backend/openvino/numpy.py,sha256=LmVuPzBjgYZ9RAuw2JeRfKcaLJSw-BOADXfvszC2F8w,65812
 keras/src/backend/openvino/random.py,sha256=bR7BYdfYHsBi5rYgCKmpFf310fa1q7JT48Z29XxhwmA,5851
 keras/src/backend/openvino/rnn.py,sha256=ErmuZLPSgG9qU-NfYPPvBZ6Ysy8k-fA4g19Vhqq7OVQ,866
 keras/src/backend/openvino/trainer.py,sha256=bMmtSALqydqdS6ke-5sYW5fgxZDshDH810p_C0xCRTg,9087
@@ -209,7 +209,7 @@ keras/src/backend/tensorflow/layer.py,sha256=iE6XYSZENEoTpNhoXrEOm7gnIOHwOjETZd_
 keras/src/backend/tensorflow/linalg.py,sha256=fpzxql1ycXIAks9AvS753aiSoaVqAuM6xbv671BulhQ,8038
 keras/src/backend/tensorflow/math.py,sha256=zTu_7Ff6B2Ro862z_xH0OCmIWbV74DjsO5UnfjYuOUQ,12370
 keras/src/backend/tensorflow/nn.py,sha256=oS7sngoA2C2SFfKQdYWvSZe7HCFfG29t4glbE6yv9CM,34616
-keras/src/backend/tensorflow/numpy.py,sha256=3KqOBtVfMf8qQ9YEqpLSZLbv5oWftvBOjNjVE8j67o0,96100
+keras/src/backend/tensorflow/numpy.py,sha256=dDJwshRZcG8jRJg82B3YbGZV-uyfHJXARPKRtha-XAs,97185
 keras/src/backend/tensorflow/optimizer.py,sha256=kFlyEOnGjEYdLpd8mpwhUeku78__xBfZbbrDWpJrq60,9307
 keras/src/backend/tensorflow/random.py,sha256=iO8V_soaDXZm9ewyAVbjudhsMj08C348c9Bz64nxXC4,6475
 keras/src/backend/tensorflow/rnn.py,sha256=99EJqbPdWddmG14zyjjhUZfU5zo9ObmslF_Mak7EmAs,34602
@@ -225,7 +225,7 @@ keras/src/backend/torch/layer.py,sha256=htECdpv9ioHWM8_zqQkEdxgDsgLu8XJi5yXgnLl-
 keras/src/backend/torch/linalg.py,sha256=2GUb107BufiHEK2zJ_fkFREo8Y8mo0OqUZLkwNNgOv4,1991
 keras/src/backend/torch/math.py,sha256=g-ElDii2Y_o1-t6BAu2nbS7JH-aPqVS5Fqds8aYzIlg,14324
 keras/src/backend/torch/nn.py,sha256=8sqbeYU1siImRRyF4J-7JEE_CvcVeGnQ4D9aGijAyxo,33379
-keras/src/backend/torch/numpy.py,sha256=8kQfqtbMwDoi9Ra8I1ykphf2ZY0-RYlMC61MfwDeBU4,55098
+keras/src/backend/torch/numpy.py,sha256=t_JTibPexzQcZ-_x27Y26cGdSDzF6k_KzggnlRAXhE4,55210
 keras/src/backend/torch/random.py,sha256=YhLfC7qkGpzlU_i6gGPVormo3BMSo7OUA3TC3GCehrA,8292
 keras/src/backend/torch/rnn.py,sha256=J0vg7ikxBiv1FzEavgwT8IVCs0ceBcEv5LYyM5C2suA,25545
 keras/src/backend/torch/trainer.py,sha256=TCnq0Tl9W0OUYesGGaSTWtGMnPiz-s6jrR5AC2F-TTg,17837
@@ -477,7 +477,7 @@ keras/src/metrics/regression_metrics.py,sha256=eLacV_8CKtzA26BJDJuncUDATuL1x8O6S
 keras/src/models/__init__.py,sha256=DPbBPSfIGgsufTfJH5U5xJOeN_Ef4FMadT7KKYg3Kjg,143
 keras/src/models/cloning.py,sha256=jwVtVVVYVasFIrln2hrzJ8bR2Xhsx9wYgEqpF1AjSvE,15786
 keras/src/models/functional.py,sha256=VqCbEAmUXdrrt2X_BdC8iUQmt-GOVtfgpTMoN8l3k-s,33667
-keras/src/models/model.py,sha256=HE-F8jSY1X-Xkkb-KH3ikI6l96Vzsc7sORWgs69rx5A,36188
+keras/src/models/model.py,sha256=mqT7eOFF2BhL0VdhtsG85-hEB3k0vwSLXAYVzvgeiA4,36178
 keras/src/models/sequential.py,sha256=CC9Q1BNB9m7TkgMHRyjOzhQvneng576wJpmdgHrACKY,14352
 keras/src/models/variable_mapping.py,sha256=FVtcgjBRqOxtvkzOE6kjG9SpcB9keDg2gS5LOTlXvG0,2181
 keras/src/ops/__init__.py,sha256=aORlvnrqY_eQl0EFLWdpHsXHnQ6JLSw1qhwJMr-VXJ0,644
@@ -489,7 +489,7 @@ keras/src/ops/linalg.py,sha256=1Z6my5X0e0uoTYPGJ0I0s2hiKbxYFmdyvoifBcZJEsc,22636
 keras/src/ops/math.py,sha256=4qYMJ5qAPmeSyeF63YWoGbUkQt6f4_VX0enOChU4mXU,37233
 keras/src/ops/nn.py,sha256=1BC-zmnpsUhqG5lSE4VvV5PsBf81wN0ZGg4kU-R8TJY,95259
 keras/src/ops/node.py,sha256=aJgn9D-GkteE--Bbt2cZ9JjVxb2W2uS1OWEKoeLsl3Y,5583
-keras/src/ops/numpy.py,sha256=ovWnm3XHDIzjiwjm_GjM0oVZHCGige7Ek95cX4qCAvk,236694
+keras/src/ops/numpy.py,sha256=xA4ozOEzgEzWlS28OnMMG6W0euvaN5lRWSL-fT65R5Y,238034
 keras/src/ops/operation.py,sha256=dpPI6bQsdBk6j0EUNygoLRHngrMTDoqT2Z55mgq6hbE,15520
 keras/src/ops/operation_utils.py,sha256=BSarr5DZF5dr-URdXNzawwZlFx6R7VRjh6P2DGwgrT4,14457
 keras/src/ops/symbolic_arguments.py,sha256=MKwXxZYkyouD9BPmQ1uUNxILdcwPvTayAqXaUV3P3o4,1628
@@ -513,11 +513,10 @@ keras/src/optimizers/sgd.py,sha256=_3xanWOI0s2dISxEVT7i_tehsWakQQz2y480Iwkonas,4
 keras/src/optimizers/schedules/__init__.py,sha256=vuUuHNTev8sD2-swsuq7zqyYbmaOhDyiIE6F3dGGSZU,546
 keras/src/optimizers/schedules/learning_rate_schedule.py,sha256=Sqvd0SRHLMilsBsVXuolElJR6z5tBTphlGJ99Yq8axw,35784
 keras/src/quantizers/__init__.py,sha256=gxZQYNL-XyUYV1BQgC6V9qVH2MpqI-R1wqhM6o2Sywo,1967
-keras/src/quantizers/gptq.py,sha256=rbRi2qmZsvYG2APg6Sh0TysXSeTop_Ehp9wRqZOW12U,14509
-keras/src/quantizers/gptq_config.py,sha256=X6HTcYSE2m0m7s3btRwgWmJ09KkhULtWtabANW7vI9Y,6766
-keras/src/quantizers/gptq_core.py,sha256=WrTTnPxMoAXTMS748ROI38FAYo46Djh9-zK3IFKTmLA,13587
-keras/src/quantizers/gptq_quant.py,sha256=ZTN7xQCULgczhdKOL-9KGEw9kyA-YmK5JItVPfa8r-w,5129
-keras/src/quantizers/quantizers.py,sha256=s-SXe9339RpcpPSIwRS-pi4HBqVpL7qr9bZnpLkDL_s,22413
+keras/src/quantizers/gptq.py,sha256=PZur5-9UFu8hhH2U8nfdz27awdKEV1NWf4V81OpxWvE,17457
+keras/src/quantizers/gptq_config.py,sha256=s_3ZCh4R-3E5l64JTuQFC13ZzqhpWFHy-tGZQa1CJxk,6382
+keras/src/quantizers/gptq_core.py,sha256=o-48-UwH6lbACvWTazuqgYKBYV-_4a148zQaT3dLz1w,14782
+keras/src/quantizers/quantizers.py,sha256=aljlsok9ISTLgn6QUfK9GJBKLqGshG6BZQTW62NzEus,29520
 keras/src/random/__init__.py,sha256=BmXVYPzxbhADohoLtAEEzB3cesP7YBFDsp1qc6BWWlg,420
 keras/src/random/random.py,sha256=bUADZIVDuCghwIWTk0qBxXTxUdiNGWIdsRi8QJ3ePg4,17581
 keras/src/random/seed_generator.py,sha256=hQTFxKSGCkGdBJHMmJj-cSRfqI3AhHtVxYT0tfOU6Fw,5590
@@ -597,7 +596,7 @@ keras/utils/bounding_boxes/__init__.py,sha256=jtvQll4u8ZY0Z96HwNhP1nxWEG9FM3gI-6
 keras/utils/legacy/__init__.py,sha256=oSYZz6uS8UxSElRaaJYWJEoweJ4GAasZjnn7fNaOlog,342
 keras/visualization/__init__.py,sha256=UKWmiy6sps4SWlmQi9WX8_Z53cPpLlphz2zIeHdwJpQ,722
 keras/wrappers/__init__.py,sha256=QkS-O5K8qGS7C3sytF8MpmO6PasATpNVGF8qtb7Ojsw,407
-keras_nightly-3.12.0.dev2025090303.dist-info/METADATA,sha256=rA14PbRaPmupzN7_lPZAarq7u9P8Zfkv8Ahlyd8YJWg,5970
-keras_nightly-3.12.0.dev2025090303.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-keras_nightly-3.12.0.dev2025090303.dist-info/top_level.txt,sha256=ptcw_-QuGZ4ZDjMdwi_Z0clZm8QAqFdvzzFnDEOTs9o,6
-keras_nightly-3.12.0.dev2025090303.dist-info/RECORD,,
+keras_nightly-3.12.0.dev2025090503.dist-info/METADATA,sha256=e94GtM-StE3GqZVta2RoPZGBYV6hQeS_ZFSlUJWJRbE,5970
+keras_nightly-3.12.0.dev2025090503.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+keras_nightly-3.12.0.dev2025090503.dist-info/top_level.txt,sha256=ptcw_-QuGZ4ZDjMdwi_Z0clZm8QAqFdvzzFnDEOTs9o,6
+keras_nightly-3.12.0.dev2025090503.dist-info/RECORD,,

keras/src/quantizers/gptq_quant.py

@@ -1,133 +0,0 @@
-from keras.src import ops
-
-
-def dequantize(input_tensor, scale, zero, maxq):
-    """The core quantization function."""
-    epsilon = ops.cast(1e-8, dtype=scale.dtype)
-    scale = ops.where(ops.equal(scale, 0), epsilon, scale)
-
-    quantized_tensor = ops.divide(input_tensor, scale)
-    quantized_tensor = ops.round(quantized_tensor)
-    q = ops.add(quantized_tensor, zero)
-    q = ops.clip(q, 0, maxq)
-
-    dequantized_tensor = ops.subtract(q, zero)
-    return ops.multiply(scale, dequantized_tensor)
-
-
-class GPTQQuantization:
-    """A class that handles the quantization of weights using GPTQ method.
-
-    This class provides methods to find quantization parameters (scale and zero)
-    for a given tensor and can be used to quantize weights in a GPTQ context.
-
-    Args:
-        weight_bits: (int) The number of bits to quantize to (e.g., 4).
-        per_channel: (bool) A flag indicating whether quantization is
-            applied per-channel (`True`) or per-tensor (`False`).
-            Defaults to `False`.
-        symmetric: (bool) A flag indicating whether symmetric (`True`) or
-            asymmetric (`False`) quantization is used. Defaults to `False`.
-        group_size: (int) The size of weight groups for quantization. A
-            value of -1 indicates that grouping is not used.
-            Defaults to -1.
-    """
-
-    def __init__(
-        self, weight_bits, per_channel=True, symmetric=False, group_size=-1
-    ):
-        self.weight_bits = weight_bits
-        self.maxq = ops.cast(
-            ops.subtract(ops.power(2, weight_bits), 1), "float32"
-        )
-        self.per_channel = per_channel
-        self.symmetric = symmetric
-        self.group_size = group_size
-
-        # These are now determined later by `find_params`
-        self.scale = None
-        self.zero = None
-
-    def find_params(self, input_tensor, weight=False):
-        """Finds quantization parameters (scale and zero) for a given tensor."""
-
-        if input_tensor is None:
-            raise ValueError("Input tensor 'input_tensor' cannot be None.")
-
-        # For weights, we typically expect at least a 2D tensor.
-        if weight and len(input_tensor.shape) < 2:
-            raise ValueError(
-                f"Input weight tensor 'input_tensor' must have a rank of at "
-                f"least 2, but got rank {len(input_tensor.shape)}."
-            )
-
-        if ops.size(input_tensor) == 0:
-            raise ValueError("Input tensor 'input_tensor' cannot be empty.")
-
-        original_shape = input_tensor.shape
-
-        if self.per_channel:
-            if weight:
-                if self.group_size != -1:
-                    input_reshaped = ops.reshape(
-                        input_tensor, [-1, self.group_size]
-                    )
-                else:
-                    input_reshaped = ops.reshape(
-                        input_tensor, [original_shape[0], -1]
-                    )
-        else:  # per-tensor
-            input_reshaped = ops.reshape(input_tensor, [1, -1])
-
-        # Find min/max values
-        min_values = ops.min(input_reshaped, axis=1)
-        max_values = ops.max(input_reshaped, axis=1)
-
-        # Apply symmetric quantization logic if enabled
-        if self.symmetric:
-            max_values = ops.maximum(ops.abs(min_values), max_values)
-            min_values = ops.where(
-                ops.less(min_values, 0), ops.negative(max_values), min_values
-            )
-
-        # Ensure range is not zero to avoid division errors
-        zero_range = ops.equal(min_values, max_values)
-        min_values = ops.where(
-            zero_range, ops.subtract(min_values, 1), min_values
-        )
-        max_values = ops.where(zero_range, ops.add(max_values, 1), max_values)
-
-        # Calculate scale and zero-point
-        self.scale = ops.divide(ops.subtract(max_values, min_values), self.maxq)
-        if self.symmetric:
-            self.zero = ops.full_like(
-                self.scale, ops.divide(ops.add(self.maxq, 1), 2)
-            )
-        else:
-            self.zero = ops.round(
-                ops.divide(ops.negative(min_values), self.scale)
-            )
-
-        # Ensure scale is non-zero
-        self.scale = ops.where(ops.less_equal(self.scale, 0), 1e-8, self.scale)
-
-        if weight:
-            # Per-channel, non-grouped case: simple reshape is correct.
-            if self.per_channel and self.group_size == -1:
-                self.scale = ops.reshape(self.scale, [-1, 1])
-                self.zero = ops.reshape(self.zero, [-1, 1])
-            elif not self.per_channel:
-                num_rows = original_shape[0]
-                self.scale = ops.tile(
-                    ops.reshape(self.scale, (1, 1)), (num_rows, 1)
-                )
-                self.zero = ops.tile(
-                    ops.reshape(self.zero, (1, 1)), (num_rows, 1)
-                )
-        if self.per_channel:
-            self.scale = ops.reshape(self.scale, [-1, 1])
-            self.zero = ops.reshape(self.zero, [-1, 1])
-
-    def ready(self):
-        """Checks if the quantization parameters have been computed."""
-        return self.scale is not None and self.zero is not None