Deprecate bytecode version 3 #57775
Closed
Deprecate bytecode version 3 #57775
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
[ghstack-poisoned]
facebook-github-bot
added
oncall: jit
Contributor
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 6b18b2d (more details on the Dr. CI page):
🕵️ 3 new failures recognized by patternsThe following CI failures do not appear to be due to upstream breakages
|
Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. [ghstack-poisoned]
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. [ghstack-poisoned]
Contributor
Author
|
@iseeyuan has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
raziel
approved these changes
May 6, 2021
Contributor
raziel
left a comment
raziel
left a comment
There was a problem hiding this comment.
Thanks.
Minor comment on whether to define a constant for the default version.
torch/csrc/jit/mobile/import.cpp
Outdated
| // introduced. The old models (some of them already in production) without | ||
| // version number don't have to be re-generated. | ||
| // version number are seen as version 3 (deprecated). | ||
| int64_t model_version = 0x3L; |
Contributor
There was a problem hiding this comment.
I'd suggest making it a constant itself (e.g. default legacy version or something like that).
Is this the only place that will use this constant?
Otherwise maybe move it to caffe2/serialize/versions.h ?
Contributor
Author
There was a problem hiding this comment.
Good catch. I'll add const here. It's the only place that it's used.
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
Contributor
Author
|
@iseeyuan has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Contributor
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
cccclai
pushed a commit
that referenced
this pull request
Mar 29, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 152531463
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
cccclai
pushed a commit
that referenced
this pull request
Apr 1, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 152759282
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
This was referenced Apr 1, 2022
cccclai
pushed a commit
that referenced
this pull request
Apr 1, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 152823050
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
cccclai
pushed a commit
that referenced
this pull request
Apr 4, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 152951819
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
cccclai
pushed a commit
that referenced
this pull request
Apr 6, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 153137729
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791) [ghstack-poisoned]
cccclai
pushed a commit
that referenced
this pull request
Apr 6, 2022
Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Differential Revision: [D28270791](https://our.internmc.facebook.com/intern/diff/D28270791/) ghstack-source-id: 153227131
facebook-github-bot
pushed a commit
that referenced
this pull request
Apr 7, 2022
Summary: Pull Request resolved: #57775 The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models. Why? * There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first. * The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low. Test Plan: Imported from OSS Reviewed By: raziel Differential Revision: D28270791 Pulled By: cccclai fbshipit-source-id: 70b1bd6352fdaae5f8d2173b81578d77018c8e44
Contributor
|
Hey @iseeyuan. |
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.
Stack from ghstack (oldest at bottom):
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models.
Why?
Differential Revision: D28270791