[inductor][ez] V.choices.get_mm_configs returns list of ChoiceCallers#161348
Closed
coconutruben wants to merge 30 commits intogh/coconutruben/49/basefrom
Closed
[inductor][ez] V.choices.get_mm_configs returns list of ChoiceCallers#161348coconutruben wants to merge 30 commits intogh/coconutruben/49/basefrom
coconutruben wants to merge 30 commits intogh/coconutruben/49/basefrom
Conversation
\# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/161348
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 23f33a1 with merge base 5babb4d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Aug 23, 2025
…oiceCallers" \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov [ghstack-poisoned]
…oiceCallers" \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov [ghstack-poisoned]
…oiceCallers" \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) [ghstack-poisoned]
Contributor
Author
|
@coconutruben has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Collaborator
|
Starting merge as part of PR stack under #162238 |
pytorchmergebot
pushed a commit
that referenced
this pull request
Sep 9, 2025
# why - enable us to override the default configs, or fall back to them through subclassing InductorChoices # what - override (private) function - default implementationt takes the kernel template choice (ktc) generator for every template and just executes the generator - future overrides can decide to replace those generators, or filter out choices - the 2nd expensive step (maybe_append_choices, choice_or_none) is handled outside this function, in the main V.choices.get_mm_configs this means that any overriding benefits from not generating expensive templates that aren't going to be used # testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520570](https://our.internmc.facebook.com/intern/diff/D81520570) Pull Request resolved: #161349 Approved by: https://github.com/eellison ghstack dependencies: #161347, #161348
pytorchmergebot
pushed a commit
that referenced
this pull request
Sep 9, 2025
…#162238) # why - unnecessary as we only ever need to know the dtype and maybe the device - we already take in the kernel inputs which have the device - enable us to specify the layout after finding all the configs but before generating the ChoiceCallers # what - replace all calls in template_heuristics that used to take Layout with now just taking out_dtype # testing ci Differential Revision: [D81820115](https://our.internmc.facebook.com/intern/diff/D81820115) Pull Request resolved: #162238 Approved by: https://github.com/eellison ghstack dependencies: #161347, #161348, #161349
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#162075, pytorch#161340, pytorch#161341, pytorch#161342, pytorch#161343, pytorch#161344, pytorch#161345, pytorch#161346, pytorch#161347
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
…eCallers (pytorch#161348)" This reverts commit c321111. Reverted pytorch#161348 on behalf of https://github.com/jeanschmidt due to Seems to have broken internal builds, see [D81520569](https://www.internalfb.com/diff/D81520569) ([comment](pytorch#161347 (comment)))
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
# why - enable us to override the default configs, or fall back to them through subclassing InductorChoices # what - override (private) function - default implementationt takes the kernel template choice (ktc) generator for every template and just executes the generator - future overrides can decide to replace those generators, or filter out choices - the 2nd expensive step (maybe_append_choices, choice_or_none) is handled outside this function, in the main V.choices.get_mm_configs this means that any overriding benefits from not generating expensive templates that aren't going to be used # testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520570](https://our.internmc.facebook.com/intern/diff/D81520570) Pull Request resolved: pytorch#161349 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
…pytorch#162238) # why - unnecessary as we only ever need to know the dtype and maybe the device - we already take in the kernel inputs which have the device - enable us to specify the layout after finding all the configs but before generating the ChoiceCallers # what - replace all calls in template_heuristics that used to take Layout with now just taking out_dtype # testing ci Differential Revision: [D81820115](https://our.internmc.facebook.com/intern/diff/D81820115) Pull Request resolved: pytorch#162238 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348, pytorch#161349
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#162075, pytorch#161340, pytorch#161341, pytorch#161342, pytorch#161343, pytorch#161344, pytorch#161345, pytorch#161346, pytorch#161347
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
…eCallers (pytorch#161348)" This reverts commit c321111. Reverted pytorch#161348 on behalf of https://github.com/jeanschmidt due to Seems to have broken internal builds, see [D81520569](https://www.internalfb.com/diff/D81520569) ([comment](pytorch#161347 (comment)))
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
# why - enable us to override the default configs, or fall back to them through subclassing InductorChoices # what - override (private) function - default implementationt takes the kernel template choice (ktc) generator for every template and just executes the generator - future overrides can decide to replace those generators, or filter out choices - the 2nd expensive step (maybe_append_choices, choice_or_none) is handled outside this function, in the main V.choices.get_mm_configs this means that any overriding benefits from not generating expensive templates that aren't going to be used # testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520570](https://our.internmc.facebook.com/intern/diff/D81520570) Pull Request resolved: pytorch#161349 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#162238) # why - unnecessary as we only ever need to know the dtype and maybe the device - we already take in the kernel inputs which have the device - enable us to specify the layout after finding all the configs but before generating the ChoiceCallers # what - replace all calls in template_heuristics that used to take Layout with now just taking out_dtype # testing ci Differential Revision: [D81820115](https://our.internmc.facebook.com/intern/diff/D81820115) Pull Request resolved: pytorch#162238 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348, pytorch#161349
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#162075, pytorch#161340, pytorch#161341, pytorch#161342, pytorch#161343, pytorch#161344, pytorch#161345, pytorch#161346, pytorch#161347
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
…eCallers (pytorch#161348)" This reverts commit c321111. Reverted pytorch#161348 on behalf of https://github.com/jeanschmidt due to Seems to have broken internal builds, see [D81520569](https://www.internalfb.com/diff/D81520569) ([comment](pytorch#161347 (comment)))
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
# why - enable us to override the default configs, or fall back to them through subclassing InductorChoices # what - override (private) function - default implementationt takes the kernel template choice (ktc) generator for every template and just executes the generator - future overrides can decide to replace those generators, or filter out choices - the 2nd expensive step (maybe_append_choices, choice_or_none) is handled outside this function, in the main V.choices.get_mm_configs this means that any overriding benefits from not generating expensive templates that aren't going to be used # testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520570](https://our.internmc.facebook.com/intern/diff/D81520570) Pull Request resolved: pytorch#161349 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
…pytorch#162238) # why - unnecessary as we only ever need to know the dtype and maybe the device - we already take in the kernel inputs which have the device - enable us to specify the layout after finding all the configs but before generating the ChoiceCallers # what - replace all calls in template_heuristics that used to take Layout with now just taking out_dtype # testing ci Differential Revision: [D81820115](https://our.internmc.facebook.com/intern/diff/D81820115) Pull Request resolved: pytorch#162238 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348, pytorch#161349
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#162075, pytorch#161340, pytorch#161341, pytorch#161342, pytorch#161343, pytorch#161344, pytorch#161345, pytorch#161346, pytorch#161347
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
…eCallers (pytorch#161348)" This reverts commit c321111. Reverted pytorch#161348 on behalf of https://github.com/jeanschmidt due to Seems to have broken internal builds, see [D81520569](https://www.internalfb.com/diff/D81520569) ([comment](pytorch#161347 (comment)))
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
…pytorch#161348) \# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520574](https://our.internmc.facebook.com/intern/diff/D81520574) Pull Request resolved: pytorch#161348 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
# why - enable us to override the default configs, or fall back to them through subclassing InductorChoices # what - override (private) function - default implementationt takes the kernel template choice (ktc) generator for every template and just executes the generator - future overrides can decide to replace those generators, or filter out choices - the 2nd expensive step (maybe_append_choices, choice_or_none) is handled outside this function, in the main V.choices.get_mm_configs this means that any overriding benefits from not generating expensive templates that aren't going to be used # testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` Differential Revision: [D81520570](https://our.internmc.facebook.com/intern/diff/D81520570) Pull Request resolved: pytorch#161349 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
…pytorch#162238) # why - unnecessary as we only ever need to know the dtype and maybe the device - we already take in the kernel inputs which have the device - enable us to specify the layout after finding all the configs but before generating the ChoiceCallers # what - replace all calls in template_heuristics that used to take Layout with now just taking out_dtype # testing ci Differential Revision: [D81820115](https://our.internmc.facebook.com/intern/diff/D81820115) Pull Request resolved: pytorch#162238 Approved by: https://github.com/eellison ghstack dependencies: pytorch#161347, pytorch#161348, pytorch#161349
Khanaksahu
pushed a commit
to Khanaksahu/pytorch-fork
that referenced
this pull request
Nov 17, 2025
\# why - every callsite just executes the generator on the spot - previous pr adds the ability to add an override before expensive generators are executed, so we don't need this generator anymore \# what - rather than yielding the ChoiceCaller, just return the list of all valid ChoiceCallers \# testing ``` python3 -bb -m pytest test/inductor/test_max_autotune.py -v ``` ghstack-source-id: c851c0e Pull Request resolved: pytorch/pytorch#161348
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):
# why
generators are executed, so we don't need this generator anymore
# what
valid ChoiceCallers
# testing
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @chenyang78 @kadeng @muchulee8 @amjames @chauhang @aakhundov
Differential Revision: D81520574