Neuron SDK Release 2.18.2 (#877)

* Neuron SDK Release 2.18.2 Release notes for Neuron SDK Release 2.18.2 --------- Co-authored-by: Liangfu Chen <[email protected]> Co-authored-by: Willis Wang <[email protected]> Co-authored-by: Esha Lakhotia <[email protected]> Co-authored-by: aws-sadaf <[email protected]> Co-authored-by: Roopnath <[email protected]>
aws-neuron · Apr 26, 2024 · d4f1951 · d4f1951
1 parent ce5bb89
commit d4f1951
Show file tree

Hide file tree

Showing 9 changed files with 128 additions and 18 deletions.
diff --git a/conf.py b/conf.py
@@ -142,7 +142,7 @@
 #top_banner_message="<span>&#9888;</span><a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/general/setup/setup-troubleshooting.html#gpg-key-update'>  Neuron repository GPG key for Ubuntu installation has expired, see instructions how to update! </a>"
 
 
-top_banner_message="Neuron 2.18.1 is released! check <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/release-notes/index.html#latest-neuron-release'> What's New  </a> and <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/general/announcements/index.html'> Announcements  </a>"
+top_banner_message="Neuron 2.18.2 is released! check <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/release-notes/index.html#latest-neuron-release'> What's New  </a> and <a class='reference internal' style='color:white;' href='https://awsdocs-neuron.readthedocs-hosted.com/en/latest/general/announcements/index.html'> Announcements  </a>"
 
 
 html_theme = "sphinx_book_theme"

diff --git a/general/announcements/neuron2.x/announce-eos-dlami.rst b/general/announcements/neuron2.x/announce-eos-dlami.rst
@@ -0,0 +1,30 @@
+.. post:: April 24, 2024
+    :language: en
+    :tags: announce-eos-dlami, neuron-dlami
+
+.. _announce-eos-dlami:
+
+Announcing end of support for Neuron Release 2.18.0 Deep Learning AMIs 
+---------------------------------------------------------------------
+
+We are announcing end of support for :ref:`Neuron release 2.18.0 <neuron-2.18.0-whatsnew>` Deep Learning AMIs. DLAMIs released between March 26,2024 (2024-03-26) and April 10, 2024 (2024-04-10) were shipped without the audit package. The following are the affected DLAMIs:
+
+Deep Learning AMI Neuron (Ubuntu 22.04) 20240401
+Deep Learning AMI Neuron PyTorch 1.13 (Amazon Linux 2) 20240328
+Deep Learning AMI Neuron PyTorch 1.13 (Amazon Linux 2) 20240402
+Deep Learning AMI Neuron PyTorch 1.13 (Amazon Linux 2) 20240409
+Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 20.04) 20240328
+Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 20.04) 20240402
+Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 20.04) 20240409
+Deep Learning AMI Neuron TensorFlow 2.10 (Amazon Linux 2) 20240328
+Deep Learning AMI Neuron TensorFlow 2.10 (Amazon Linux 2) 20240402
+Deep Learning AMI Neuron TensorFlow 2.10 (Amazon Linux 2) 20240409
+Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 20.04) 20240328
+Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 20.04) 20240402
+Deep Learning AMI Neuron TensorFlow 2.10 (Ubuntu 20.04) 20240409
+Deep Learning Base Neuron AMI (Amazon Linux 2) 20240401
+Deep Learning Base Neuron AMI (Amazon Linux 2) 20240408
+Deep Learning Base Neuron AMI (Ubuntu 20.04) 20240401
+Deep Learning Base Neuron AMI (Ubuntu 20.04) 20240408
+
+Current users of the above :ref:`Neuron release 2.18 <neuron-2.18.0-whatsnew>` Deep Learning AMIs are required to upgrade to the latest DLAMIs in order to consume those with the audit package installed. For instructions to upgrade to the latest AMI, see the :ref:`DLAMI User Guide <neuron-dlami-overview>` or find the specific DLAMI image id for the latest Neuron release with :ref:`SSM parameters <ssm-parameter-neuron-dlami>`.
diff --git a/general/announcements/neuron2.x/announce-eos-multiframework-dlamis-inf1.rst b/general/announcements/neuron2.x/announce-eos-multiframework-dlamis-inf1.rst
@@ -0,0 +1,19 @@
+.. post:: April 24, 2024
+    :language: en
+    :tags: announce-eos-dlamis-inf1, dlami-inf1
+
+.. _announce-update-multiframework-dlami:
+
+Announcing end of support for Neuron virtual environments in AWS Deep Learning AMI (Amazon Linux 2)
+----------------------------------------------------------------------------------------------------
+
+:ref:`Neuron release 2.18.2 <neuron-2.18.2-whatsnew>` will be the last release that will include support for the following virtual environments in AWS Deep Learning AMI (Amazon Linux 2):
+
+``aws_neuron_pytorch_p38: PyTorch 1.13, Python 3.8``
+``aws_neuron_tensorflow2_p38: TensorFlow 2.10, Python 3.8``
+
+Future releases will not include Neuron support for these virtual environments.
+
+Current users of Neuron virtual environments in `AWS Deep Learning AMI (Amazon Linux 2) <https://aws.amazon.com/releasenotes/aws-deep-learning-ami-amazon-linux-2/>`_ are required to migrate to the `Neuron multi framework DLAMI <https://aws.amazon.com/releasenotes/aws-deep-learning-ami-neuron-ubuntu-22-04/>`_.
+
+To see a list of Neuron supported virtual environments, please refer to :ref:`Neuron Multi Framework DLAMI User Guide <neuron-dlami-overview>`.
diff --git a/...ormers-neuronx/transformers-neuronx-developer-guide-for-continuous-batching.rst b/...ormers-neuronx/transformers-neuronx-developer-guide-for-continuous-batching.rst
@@ -62,7 +62,7 @@ In the following example we demonstrate how to perform continuous batching with
     
     # Create an LLM.
     llm = LLM(
-        model="openlm-research/open_llama_3b",
+        model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
         max_num_seqs=8,
         # The max_model_len and block_size arguments are required to be same as max sequence length,
         # when targeting neuron device. Currently, this is a known limitation in continuous batching
@@ -71,7 +71,8 @@ In the following example we demonstrate how to perform continuous batching with
         block_size=128,
         # The device can be automatically detected when AWS Neuron SDK is installed.
         # The device argument can be either unspecified for automated detection, or explicitly assigned.
-        device="neuron")
+        device="neuron",
+        tensor_parallel_size=2)
     # Generate texts from the prompts. The output is a list of RequestOutput objects
     # that contain the prompt, generated text, and other information.
     outputs = llm.generate(prompts, sampling_params)

diff --git a/neuron-runtime/nrt-configurable-parameters.rst b/neuron-runtime/nrt-configurable-parameters.rst
@@ -49,7 +49,7 @@ configure NeuronX Runtime behavior.
      - Timeout for execution in seconds
      - Integer
      - 0 to INT_MAX
-     - 30 on inf1, 600 on trn1/inf2
+     - 30
      - 2.0+
    * - ``NEURON_RT_VALIDATE_HASH``
      - Validate NEFF contents before loading into accelerator

diff --git a/release-notes/compiler/neuronx-cc/index.rst b/release-notes/compiler/neuronx-cc/index.rst
@@ -8,6 +8,12 @@ Neuron Compiler (``neuronx-cc``) release notes
    :depth: 2
 
 
+Neuron Compiler [2.13.72.0]
+----------------------------
+Date: 04/25/2024
+
+* Minor bug fixes and enhancements
+
 
 Neuron Compiler [2.13.68.0]
 ----------------------------

diff --git a/release-notes/index.rst b/release-notes/index.rst
@@ -11,6 +11,12 @@ What's New
 .. _neuron-2.18.0-whatsnew:
 
 
+Neuron 2.18.2 (04/25/2024)
+--------------------------
+Patch release with minor Neuron Compiler bug fixes and enhancements. See more in  :ref:`neuronx-cc-rn`
+
+
+
 Neuron 2.18.1 (04/10/2024)
 --------------------------
 
@@ -343,27 +349,27 @@ Release Artifacts
 Trn1 packages
 ^^^^^^^^^^^^^^
 
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=trn1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=trn1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.2
 
 Inf2 packages
 ^^^^^^^^^^^^^^
 
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.2
 
 Inf1 packages
 ^^^^^^^^^^^^^^
 
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.2
 
 Supported Python Versions for Inf1 packages
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=pyversions --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=pyversions --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.2
 
 Supported Python Versions for Inf2/Trn1 packages
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=pyversions --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=pyversions --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.2
 
 Supported Numpy Versions
 ^^^^^^^^^^^^^^^^^^^^^^^^

diff --git a/release-notes/prev/content.rst b/release-notes/prev/content.rst
@@ -7,20 +7,20 @@ Previous Releases Artifacts (Neuron 2.x)
    :local:
    :depth: 1
 
-Neuron 2.18.0 (04/01/2024)
+Neuron 2.18.1 (04/10/2024)
 ---------------------------
 
 Trn1 packages
 ^^^^^^^^^^^^^
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=trn1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.0
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=trn1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
 
 Inf2 packages
 ^^^^^^^^^^^^^
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.0
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf2 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
 
 Inf1 packages
 ^^^^^^^^^^^^^
-.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.0
+.. program-output:: python3 src/helperscripts/n2-helper.py --list=packages --instance=inf1 --file=src/helperscripts/n2-manifest.json --neuron-version=2.18.1
 
 
 Neuron 2.17.0 (02/13/2024)

diff --git a/src/helperscripts/n2-manifest.json b/src/helperscripts/n2-manifest.json
@@ -4,13 +4,13 @@
       {"repo_type":"rpm", "repo_url":"https://yum.repos.neuron.amazonaws.com/"},
       {"repo_type":"deb", "repo_url":"https://apt.repos.neuron.amazonaws.com/"}
     ],
-    "manifest_date": "04/10/2024",
-    "manifest_version": "2.18.1",
+    "manifest_date": "04/25/2024",
+    "manifest_version": "2.18.2",
     "latest_release": [
       {"instance":"inf1", "version":"2.18.0"},
-      {"instance":"trn1", "version":"2.18.1"},
-      {"instance":"inf2", "version":"2.18.1"},
-      {"instance":"trn1n", "version":"2.18.1"}
+      {"instance":"trn1", "version":"2.18.2"},
+      {"instance":"inf2", "version":"2.18.2"},
+      {"instance":"trn1n", "version":"2.18.2"}
     ],
     "os_properties": [
       {"os":"ubuntu18", "default_python_version":"3.7"},
@@ -86,6 +86,54 @@
       {"name":"neuronx_distributed","component":"Neuron Distributed","category":"na","package_type":"os","use_cases":["inference","training"],"pin_major":"false"}
     ],
     "neuron_releases": [
+      {"neuron_version":"2.18.2", "packages": [
+        {"name":"aws-neuronx-collectives","version":"2.20.22.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-dkms","version":"2.16.7.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-gpsimd-customop-lib","version":"0.9.1.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-gpsimd-tools","version":"0.9.0.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-k8-plugin","version":"2.20.13.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-k8-scheduler","version":"2.20.13.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-oci-hook","version":"2.3.0.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-runtime-discovery","version":"2.9","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"aws-neuronx-runtime-lib","version":"2.20.22.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
+        {"name":"aws-neuronx-tools","version":"2.17.1.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"dmlc_nnvm","version":"1.19.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"dmlc_topi","version":"1.19.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"dmlc_tvm","version":"1.19.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"inferentia_hwm","version":"1.17.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"libneuronxla","version":"2.0.965","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"libneuronxla","version":"0.5.971","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"mx_neuron","version":"1.8.0.2.4.50.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"mxnet_neuron","version":"1.5.1.1.10.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"neuron-cc","version":"1.22.0.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"neuronperf","version":"1.8.55.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"neuronx-cc","version":"2.13.72.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"neuronx_distributed","version":"0.7.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorboard-plugin-neuronx","version":"2.6.7.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
+        {"name":"tensorflow-model-server-neuronx","version":"2.10.1.2.10.19.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"tensorflow-model-server-neuronx","version":"2.7.4.2.10.19.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"tensorflow-model-server-neuronx","version":"2.8.4.2.10.19.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"tensorflow-model-server-neuronx","version":"2.9.3.2.10.19.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},
+        {"name":"tensorflow-neuron","version":"2.10.1.2.10.19.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuron","version":"2.7.4.2.10.19.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuron","version":"2.8.4.2.10.19.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuron","version":"2.9.3.2.10.19.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuronx","version":"2.10.1.2.1.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuronx","version":"2.7.4.2.1.0","supported_instances":["trn1","inf."],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuronx","version":"2.8.4.2.1.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"tensorflow-neuronx","version":"2.9.3.2.1.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuron","version":"1.10.2.2.9.74.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuron","version":"1.11.0.2.9.74.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuron","version":"1.12.1.2.9.74.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuron","version":"1.13.1.2.9.74.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuron","version":"1.9.1.2.9.74.0","supported_instances":["inf1"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuronx","version":"1.13.1.1.14.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch-neuronx","version":"2.1.2.2.1.0","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch_xla","version":"1.13.1+torchneurone","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"torch_xla","version":"2.1.2","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"transformers-neuronx","version":"0.10.0.360","supported_instances":["trn1","inf2"],"supported_python_versions":["3.8","3.9","3.10"]},
+        {"name":"efa-installer","version":"na","supported_instances":["trn1"],"supported_python_versions":[]}
+      ]},
       {"neuron_version":"2.18.1", "packages": [
         {"name":"aws-neuronx-collectives","version":"2.20.22.0","supported_instances":["trn1","inf2"],"supported_python_versions":[]},
         {"name":"aws-neuronx-dkms","version":"2.16.7.0","supported_instances":["inf1","trn1","inf2"],"supported_python_versions":[]},