[CD][CUDA][Triton][PTXAS] Turn on BUILD_BUNDLE_PTXAS=1 for CUDA13 X86 Wheel Build #163972
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
builds because triton by default ships CUDA12.8 ptxas
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/163972
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 6 PendingAs of commit 2979396 with merge base 5880996 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
atalman
approved these changes
Sep 26, 2025
malfet
approved these changes
Sep 26, 2025
Contributor
There was a problem hiding this comment.
LGTM, but please update test plan
And propose followup PR for aarch64
Collaborator
Author
Thanks @malfet ! I updated the test plan and changed the title to reflect this is only x86. I will create a follow up for ARM CUDA13 wheel build, thanks for catching it! |
nWEIdia
added a commit
to nWEIdia/pytorch
that referenced
this pull request
Sep 26, 2025
…UDA13 Wheel Build See also pytorch#163972
Collaborator
Author
|
Considering the original issue all seem to derive from ARM systems (e.g. THOR). |
Collaborator
Author
|
Closing as the new ptxas that comes with cuda13 is mostly dealing with ARM based GPU addition. So having a cuda13 ptxas in x86 cuda binary does not have clear help. |
pytorchmergebot
pushed a commit
that referenced
this pull request
Sep 30, 2025
…63988) See also #163972, which was intended to be this PR. Triton (release/3.5.x) by default ships CUDA12.8 ptxas. This PR tries to bundle a ptxas version for cuda13, so that it can help #163801 when users run on new devices like THOR and Spark. Fixes #163801 Test Plan: Check binary size increase against nightly or v2.9RC Install the binary from into a working THOR and GB200/GH100 machine (reproduce the original issue first on THOR), then install the binary built from this PR and we expect the issue to be gone without any additional user setting. Testing on GB200 is to ensure no regression. Reference: #119750 and pytorch/builder@5c814e2 Note: with this PR, the pytorch world's torch.compile is supposed to find ptxas via "torch/_inductor/runtime/compile_tasks.py" and "_set_triton_ptxas_path". Use cases that do not go through "_set_triton_ptxas_path" may not be able to use the cuda13 ptxas binary. However, as is, the triton world does not know the existence of this new cuda13 ptxas. So IF a users thinks there is already pytorch/bin/ptxas and delete the ptxas from triton, then https://github.com/triton-lang/triton/blob/c6ad34f7eb42630533412d93ca2cc00a4b4f8f3c/python/triton/knobs.py#L216 would still complain ptxas not found (if removed - it won't know this new one available) Pull Request resolved: #163988 Approved by: https://github.com/atalman
pytorchbot
pushed a commit
that referenced
this pull request
Sep 30, 2025
…63988) See also #163972, which was intended to be this PR. Triton (release/3.5.x) by default ships CUDA12.8 ptxas. This PR tries to bundle a ptxas version for cuda13, so that it can help #163801 when users run on new devices like THOR and Spark. Fixes #163801 Test Plan: Check binary size increase against nightly or v2.9RC Install the binary from into a working THOR and GB200/GH100 machine (reproduce the original issue first on THOR), then install the binary built from this PR and we expect the issue to be gone without any additional user setting. Testing on GB200 is to ensure no regression. Reference: #119750 and pytorch/builder@5c814e2 Note: with this PR, the pytorch world's torch.compile is supposed to find ptxas via "torch/_inductor/runtime/compile_tasks.py" and "_set_triton_ptxas_path". Use cases that do not go through "_set_triton_ptxas_path" may not be able to use the cuda13 ptxas binary. However, as is, the triton world does not know the existence of this new cuda13 ptxas. So IF a users thinks there is already pytorch/bin/ptxas and delete the ptxas from triton, then https://github.com/triton-lang/triton/blob/c6ad34f7eb42630533412d93ca2cc00a4b4f8f3c/python/triton/knobs.py#L216 would still complain ptxas not found (if removed - it won't know this new one available) Pull Request resolved: #163988 Approved by: https://github.com/atalman (cherry picked from commit 3b4ad4a)
atalman
pushed a commit
that referenced
this pull request
Sep 30, 2025
…64236) [AARCH64][CD][CUDA13][Triton][PTXAS] Turn on BUILD_BUNDLE_PTXAS=1 (#163988) See also #163972, which was intended to be this PR. Triton (release/3.5.x) by default ships CUDA12.8 ptxas. This PR tries to bundle a ptxas version for cuda13, so that it can help #163801 when users run on new devices like THOR and Spark. Fixes #163801 Test Plan: Check binary size increase against nightly or v2.9RC Install the binary from into a working THOR and GB200/GH100 machine (reproduce the original issue first on THOR), then install the binary built from this PR and we expect the issue to be gone without any additional user setting. Testing on GB200 is to ensure no regression. Reference: #119750 and pytorch/builder@5c814e2 Note: with this PR, the pytorch world's torch.compile is supposed to find ptxas via "torch/_inductor/runtime/compile_tasks.py" and "_set_triton_ptxas_path". Use cases that do not go through "_set_triton_ptxas_path" may not be able to use the cuda13 ptxas binary. However, as is, the triton world does not know the existence of this new cuda13 ptxas. So IF a users thinks there is already pytorch/bin/ptxas and delete the ptxas from triton, then https://github.com/triton-lang/triton/blob/c6ad34f7eb42630533412d93ca2cc00a4b4f8f3c/python/triton/knobs.py#L216 would still complain ptxas not found (if removed - it won't know this new one available) Pull Request resolved: #163988 Approved by: https://github.com/atalman (cherry picked from commit 3b4ad4a) Co-authored-by: Wei Wang <weiwan@nvidia.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Triton (release/3.5.x) by default ships CUDA12.8 ptxas.
This PR tries to bundle a ptxas version for cuda13, so that it can help #163801 when users run on new devices like THOR and Spark.
Fixes #163801
Test Plan:
[Update: since the original ptxas issue seems to be an ARM specific issue - THOR device is on ARM], This PR seems not appropriate.
Reference: #119750 and pytorch/builder@5c814e2
cc @ptrblck @eqy @tinglvv @atalman @malfet