Change aot_module_simplified to take take arguments directly#89669
Closed
ezyang wants to merge 11 commits intogh/ezyang/1588/basefrom
Closed
Change aot_module_simplified to take take arguments directly#89669ezyang wants to merge 11 commits intogh/ezyang/1588/basefrom
ezyang wants to merge 11 commits intogh/ezyang/1588/basefrom
Conversation
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyang@fb.com> [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/89669
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 FailuresAs of commit adf590f: The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Nov 25, 2022
Closed
Closed
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
Contributor
Author
|
failure here looks legit |
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
ezyang
added a commit
that referenced
this pull request
Nov 25, 2022
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> ghstack-source-id: 49f39c5 Pull Request resolved: #89669
voznesenskym
approved these changes
Nov 25, 2022
| *params_flat, | ||
| *args, | ||
| ) | ||
| compiled_fn = create_aot_dispatcher_function( |
Collaborator
There was a problem hiding this comment.
can you underscore create_aot_dispatcher_function like in the source PR?
Contributor
Author
There was a problem hiding this comment.
You're welcome to underscore functions in a follow up PR, there's a lot more identifiers than create_aot_dispatcher_function that need underscoring, and underscoring the function here contributed unnecessary line noise to the PR
Contributor
Author
There was a problem hiding this comment.
In general, the functorch convention is that all identifiers in functorch/_src are considered private (even if the identifier doesn't have a leading underscore), and public identifiers are selectively reexported in functorch itself). So it is unnecessary to mark identifiers private on a one-by-one basis.
voznesenskym
approved these changes
Nov 25, 2022
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This was referenced Nov 26, 2022
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
Closed
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
This is extracted from voz's #89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyangfb.com> cc mlazos soumith voznesenskym yanboliang penguinwu anijain2305 EikanWang jgong5 Guobing-Chen chunyuan-w XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx desertfire [ghstack-poisoned]
Chillee
approved these changes
Nov 28, 2022
Collaborator
Chillee
left a comment
There was a problem hiding this comment.
Discussed this change with Voz previously, makes sense.
| aot_config, | ||
| ) | ||
|
|
||
| # TODO: There is something deeply wrong here; compiled_fn running with |
Collaborator
There was a problem hiding this comment.
I don't think compiled_fn actually returns the boxed calling convention (compiled_fn here should be the autograd.Function object, not the callable returned from the backend.
Contributor
Author
There was a problem hiding this comment.
It gets boxed up here
if needs_autograd:
return make_boxed_func(
aot_dispatch_autograd(flat_fn, fake_flat_tensor_args, aot_config)
)
Closed
kulinseth
pushed a commit
to kulinseth/pytorch
that referenced
this pull request
Dec 10, 2022
…#89669) This is extracted from voz's pytorch#89392 Previously, the implementation did some half-assed caching where it returned a callable, that when invoked for the first time, actually performed the compilation. Delaying the compilation like this... seems totally unnecessary? To make matters worse, this has cost (we have to check if we hit the cache) and unsound (because the compiled function may not be valid for other arguments.) So instead, we ask user to provide arguments, and compile everything immediately. Signed-off-by: Edward Z. Yang <ezyang@fb.com> Pull Request resolved: pytorch#89669 Approved by: https://github.com/voznesenskym, https://github.com/Chillee
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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):
This is extracted from voz's #89392
Previously, the implementation did some half-assed caching where it
returned a callable, that when invoked for the first time, actually
performed the compilation. Delaying the compilation like this...
seems totally unnecessary? To make matters worse, this has cost
(we have to check if we hit the cache) and unsound (because the
compiled function may not be valid for other arguments.)
So instead, we ask user to provide arguments, and compile everything
immediately.
Signed-off-by: Edward Z. Yang ezyang@fb.com
cc @mlazos @soumith @voznesenskym @yanboliang @penguinwu @anijain2305 @EikanWang @jgong5 @Guobing-Chen @chunyuan-w @XiaobingSuper @zhuhaozhe @blzheng @Xia-Weiwen @wenzhe-nrv @jiayisunx @desertfire