You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
While using HuggingFace Transformers Trainer API to train (i.e. :ref:`HuggingFace Trainer API fine-tuning tutorial<torch-hf-bert-finetune>`), you may see the error "Attempted to access the data pointer on an invalid python storage". This is a known `issue <https://github.com/huggingface/transformers/issues/2.678>`_ and has been fixed in the version ``4.37.3`` of HuggingFace Transformers.
While using HuggingFace Transformers Trainer API to train (i.e. :ref:`HuggingFace Trainer API fine-tuning tutorial<torch-hf-bert-finetune>`), you may see the error "Attempted to access the data pointer on an invalid python storage". This is a known `issue <https://github.com/huggingface/transformers/issues/27778>`_ and has been fixed in the version ``4.37.3`` of HuggingFace Transformers.
While using HuggingFace Transformers Trainer API to train (i.e. :ref:`HuggingFace Trainer API fine-tuning tutorial<torch-hf-bert-finetune>`), you may see the error "Attempted to access the data pointer on an invalid python storage". This is a known `issue <https://github.com/huggingface/transformers/issues/27778>`_ and has been fixed in the version ``4.37.3`` of HuggingFace Transformers.
174
174
175
175
``Input dimension should be either 1 or equal to the output dimension it is broadcasting into`` or ``IndexError: index out of range`` error during Neuron Parallel Compile
While using HuggingFace Transformers Trainer API to train (i.e. :ref:`HuggingFace Trainer API fine-tuning tutorial<torch-hf-bert-finetune>`), you may see the error "Attempted to access the data pointer on an invalid python storage". This is a known `issue <https://github.com/huggingface/transformers/issues/27578>`_ and has been fixed in the version ``4.37.3`` of HuggingFace Transformers.
188
189
189
190
``ImportError: libcrypt.so.1: cannot open shared object file: No such file or directory`` on Amazon Linux 2023
Copy file name to clipboardExpand all lines: conf.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -214,7 +214,7 @@ def get_env_vars():
214
214
215
215
# top_banner_message="<span>⚠</span><a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/setup/setup-troubleshooting.html#gpg-key-update'> Neuron repository GPG key for Ubuntu installation has expired, see instructions how to update! </a>"
216
216
217
-
top_banner_message="Neuron 2.26.0 is released! Check <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/release-notes/index.html'>What's New </a> and <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/about-neuron/announcements/index.html'>Announcements</a> for more details."
217
+
top_banner_message="Neuron 2.26.1 is released! Check <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/release-notes/index.html'>What's New </a> and <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/about-neuron/announcements/index.html'>Announcements</a> for more details."
Copy file name to clipboardExpand all lines: dlami/index.rst
+8-94Lines changed: 8 additions & 94 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,67 +20,9 @@ Neuron Multi Framework DLAMI
20
20
Neuron Deep Learning AMI (DLAMI) is a multi-framework DLAMI that supports multiple Neuron framework/libraries. Each DLAMI is pre-installed with Neuron drivers and support all Neuron instance types. Each virtual environment that corresponds to a specific Neuron framework/library
21
21
comes pre-installed with all the Neuron libraries including Neuron compiler and Neuron runtime needed for you to easily get started.
22
22
23
-
24
-
.. note::
25
-
26
-
Tensorflow-neuron 2.10 (inf1) released in SDK v2.20.2 is not compatible with the latest runtime in v2.21 SDK.
27
-
Code that compiles will face runtime errors with the latest SDK 2.21.1 version.
28
-
29
-
Neuron team is aware of this issue and we will ship a single-framework AMI for TF 2.10 inf1 in a future release.
30
-
31
-
You can use multi-framework DLAMIs from Neuron SDK v2.20.0 for inf1 workloards to avoid this issue. For example:
32
-
33
-
Deep Learning AMI Neuron (Ubuntu 22.04/AL2023) 20241027
34
-
35
-
|Ubuntu22: ami-017ff4652165fd617
36
-
|AL2023: ami-06fdb253ce8a32239
37
-
38
-
.. code-block:: shell
39
-
40
-
aws ec2 run-instances --image-id <ami-id>
41
-
42
-
43
-
Alternatively, you can use the latest Neuron DLAMIs on Ubuntu and run this command as a work-around:
https://github.com/aws-neuron/aws-neuron-sdk/issues/1071 for more information on the issue.
54
-
55
-
56
23
.. note::
57
-
58
-
The AL2023 DLAMI shipped in SDK v2.25 has an issue with the symbolic linking of Python3.10 shared object files which affects PyTorch virtual environments.
59
-
This is because AL2023 operating system comes with Python3.9 by default and torch_neuronx requires Python3.10. We have fixed the issue in the upcoming release.
Within the PyTorch 2.8 NxD Training virtual environment, we have included a setup script that installs required dependencies for the package. To run this script,
145
81
activate the virtual environment and run ``setup_nxdt.sh`` and this will run :ref:`the setup steps here <nxdt_installation_guide>`.
@@ -190,18 +126,7 @@ Single Framework DLAMIs supported
190
126
* - Tensorflow 2.10
191
127
- Ubuntu 22.04
192
128
- Inf2, Trn1, Trn1n, Trn2
193
-
- Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 22.04)
194
-
195
-
* - Tensorflow 2.10 (Inf1)
196
-
- Ubuntu 22.04
197
-
- Inf1
198
-
- Deep Learning AMI Neuron TensorFlow 2.10 Inf1 (Ubuntu 22.04)
199
-
200
-
* - PyTorch 1.13 (Inf1)
201
-
- Ubuntu 22.04
202
-
- Inf1
203
-
- Deep Learning AMI Neuron PyTorch 1.13 Inf1 (Ubuntu 22.04)
204
-
129
+
- Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 22.04)
* - Deep Learning AMI Neuron JAX 0.6 (Ubuntu 22.04, Amazon Linux 2023)
232
157
- JAX NeuronX 0.6
233
158
- /opt/aws_neuronx_venv_jax_0_6
234
-
235
-
* - Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 22.04)
236
-
- Pytorch Neuron (Inf1)
237
-
- /opt/aws_neuron_venv_pytorch_1_13_inf1
238
159
239
160
* - Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 22.04)
240
161
- Tensorflow Neuronx
241
162
- /opt/aws_neuronx_venv_tensorflow_2_10
242
-
243
-
* - Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 22.04)
244
-
- Tensorflow Neuron (Inf1)
245
-
- /opt/aws_neuron_venv_tensorflow_2_10_inf1
246
-
163
+
247
164
248
165
You can easily get started with the single framework DLAMI through AWS console by following one of the corresponding setup guides . If you are looking to
249
166
use the Neuron DLAMI in your cloud automation flows , Neuron also supports :ref:`SSM parameters <ssm-parameter-neuron-dlami>` to easily retrieve the latest DLAMI id.
@@ -267,11 +184,11 @@ Base DLAMIs supported
267
184
- DLAMI Name
268
185
269
186
* - Amazon Linux 2023
270
-
- Inf1, Inf2, Trn1n, Trn1, Trn2
187
+
- Inf2, Trn1n, Trn1, Trn2
271
188
- Deep Learning Base Neuron AMI (Amazon Linux 2023)
272
189
273
190
* - Ubuntu 22.04
274
-
- Inf1, Inf2, Trn1n, Trn1, Trn2
191
+
- Inf2, Trn1n, Trn1, Trn2
275
192
- Deep Learning Base Neuron AMI (Ubuntu 22.04)
276
193
277
194
@@ -333,9 +250,6 @@ SSM Parameter Prefix
333
250
* - Deep Learning AMI Neuron JAX 0.6 (Amazon Linux 2023)
0 commit comments