[Inductor]: Support updated Triton AttrsDescriptor
#137757
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/137757
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7589056 with merge base 3b77103 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@pytorchbot label "topic: not user facing" |
torch/_inductor/runtime/hints.py
Outdated
There was a problem hiding this comment.
Let's add some asserts to ensure things don't change over time (or with different backends). For example:
assert res.property_values["tt.divisibility"] == 16
assert res.property_values["tt.equal_to"] == 1
If that changes, this code will be incorrect.
mikaylagawarecki
added
the
triaged
alexbaden
force-pushed
the
alex/support_new_attrs_descriptor
branch
from
78524d6 to
7589056
Compare
|
@jansel I rebased and addressed your change request. Please let me know if this needs anything else. |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
5 participants
The Triton
AttrsDescriptorobject was refactored in triton-lang/triton#4734. These changes add support for the newAttrsDescriptorwhile maintaining backwards compatibility with the existing version. The main changes are different names for the initialized of the descriptor parameters, and a creation via a static method instead of the class constructor.Depends on #137458 which removes some unused logic around the old descriptor. Those changes make this PR cleaner, but if for some reason that old logic is still used I can make adjustments.
Use of the new
AttrsDescriptordepends on triton-lang/triton#4888cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @chauhang