changed PT and TF versions #806
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
DvirDukhan
changed the title
Codecov Report
@@ Coverage Diff @@
## master #806 +/- ##
==========================================
+ Coverage 81.33% 81.34% +0.01%
==========================================
Files 56 56
Lines 8185 8192 +7
==========================================
+ Hits 6657 6664 +7
Misses 1528 1528
Continue to review full report at Codecov.
|
chayim
previously approved these changes
Jul 11, 2021
alonre24
reviewed
Jul 11, 2021
alonre24
previously approved these changes
Jul 11, 2021
chayim
reviewed
Oct 10, 2021
chayim
reviewed
Oct 10, 2021
DvirDukhan
commented
Oct 12, 2021
| ###### SET VERSIONS ###### | ||
|
|
||
| ORT_VERSION="1.9.0" | ||
| DLPACK_VERSION="v0.5_RAI" |
There was a problem hiding this comment.
are we on 0.5 or 0.6?
There was a problem hiding this comment.
dlack released 0.6 about 3 months ago but nothing has changed except for the version number. Our fork is up to date (except for our additions), so I don't see a reason to upgrade our fork at this point...
chayim
reviewed
Oct 13, 2021
| @@ -30,8 +30,8 @@ ARG ONNXRUNTIME_VER={{REDIS_ONNX_VERSION}} | |||
| # build | |||
| WORKDIR /build | |||
| {% if REDIS_GPU is defined %} | |||
| {% set BUILDTYPE="MinSizeRel" %} | |||
| {% set BUILDARGS="--use_cuda --cudnn_home /usr/local/cuda --cuda_home /usr/local/cuda" %} | |||
| {% set BUILDTYPE="Release" %} | |||
There was a problem hiding this comment.
Are you sure about this? I admit that I don't know - but literally lifted it from the old docker builds.
There was a problem hiding this comment.
Yes it's OK, I checked it.
chayim
reviewed
Oct 13, 2021
docs/developer-backends.md
Outdated
|
|
||
| ------- | ||
|
|
||
| ## Backends | ||
|
|
||
| ### onnxruntime | ||
|
|
||
| We build Onnxruntime library with DISABLE_EXTERNAL_INITIALIZERS=ON build flag. This means that loading ONNX models that use external files to store the initial (usually very large) values of the model's operations, is invalid. That is, initializers values must be part of the serialized model, which is also the standard use case. |
There was a problem hiding this comment.
We build the onnxruntime library with the DISABLE_EXTERNAL_INITIALIZERS=ON build flag. As a result, loading ONNX models that use external files to store the initial (usually very large) values of the model's operations, is invalid. Hence, initialization values must be part of the serialized model, which is also the standard use case.
chayim
reviewed
Oct 13, 2021
docs/developer-backends.md
Outdated
| sudo apt install python3 python3-dev make docker | ||
| python3 -m venv /path/to/venv | ||
| source /path/to/venv/bin/activate | ||
| pip install jinja |
There was a problem hiding this comment.
sudo apt install python3 python3-dev make docker
python3 -m venv /path/to/venv
source /path/to/venv/bin/activate
pip install jinja2
chayim
reviewed
Oct 13, 2021
docs/developer-backends.md
Outdated
|
|
||
| GNU Make is used as a runner for the dockerfile generator. Python is the language used for the generator script, and jinja is the templating library used to create the docker file from the template. | ||
| GNU Make is used as a runner for the dockerfile generator. Python is the language used for the generator script, and jinja is the templating library used to create the docker file from a template *dockerfile.tmpl* that can be found in the directory of a given backend listed below. |
There was a problem hiding this comment.
GNU Make is used as a runner for the dockerfile generator. Python is the language used for the generator script, and jinja is the templating library used to create the docker file from the template *dockerfile.tmpl*, located in the directory for the backends listed below.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Upgrade to TF 2.6, PT 1.9.
TF requires CUDA 11.2, so we update CI image for testing with GPU.
In one test, error message is changed in GPU version of TF due to the upgrade.
Here we also remove all the build (and fetch) logic for OS and architectures that are not in used for our backends currently (also update documentation accordingly). The work that been done so far is in #851 draft PR, from which we can continue in the future for adding such support.