[BLAS] Avoid downcasts for fp16fp16->fp32 BLAS #161999
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/161999
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 3 PendingAs of commit c3df264 with merge base 6737e2c ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
malfet
added a commit
that referenced
this pull request
Sep 2, 2025
malfet
added
module: linear algebra
malfet
added
release notes: linalg_frontend
drisspg
approved these changes
Sep 3, 2025
|
Starting merge as part of PR stack under #162001 |
pytorchmergebot
pushed a commit
that referenced
this pull request
Sep 3, 2025
Followup after #154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: #162001 Approved by: https://github.com/drisspg ghstack dependencies: #161999
|
@pytorchbot revert -m "break a few internal tests" -c ghfirst |
|
@pytorchbot successfully started a revert job. Check the current status here. |
pytorchmergebot
added a commit
that referenced
this pull request
Sep 4, 2025
This reverts commit b40d943. Reverted #162001 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](#161999 (comment)))
pytorchmergebot
added a commit
that referenced
this pull request
Sep 4, 2025
This reverts commit 02c83f1. Reverted #161999 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](#161999 (comment)))
|
@malfet your PR has been successfully reverted. |
|
@pytorchbot merge -f "Not sure why it was reverted in the 1st place..." |
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
This reverts commit b40d943. Reverted pytorch#162001 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
This reverts commit 02c83f1. Reverted pytorch#161999 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
Discovered while debugging pytorch#160841 where sdpa returned NaNs, because during the computation intermediate values were cast back to fp16 before normalization, which was fixed by pytorch#161999 ) Pull Request resolved: pytorch#162401 Approved by: https://github.com/Skylion007, https://github.com/drisspg
markc-614
pushed a commit
to markc-614/pytorch
that referenced
this pull request
Sep 17, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
This reverts commit b40d943. Reverted pytorch#162001 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
This reverts commit 02c83f1. Reverted pytorch#161999 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Discovered while debugging pytorch#160841 where sdpa returned NaNs, because during the computation intermediate values were cast back to fp16 before normalization, which was fixed by pytorch#161999 ) Pull Request resolved: pytorch#162401 Approved by: https://github.com/Skylion007, https://github.com/drisspg
mansiag05
pushed a commit
to mansiag05/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
This reverts commit b40d943. Reverted pytorch#162001 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
This reverts commit 02c83f1. Reverted pytorch#161999 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
Discovered while debugging pytorch#160841 where sdpa returned NaNs, because during the computation intermediate values were cast back to fp16 before normalization, which was fixed by pytorch#161999 ) Pull Request resolved: pytorch#162401 Approved by: https://github.com/Skylion007, https://github.com/drisspg
cleonard530
pushed a commit
to cleonard530/pytorch
that referenced
this pull request
Sep 22, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
This reverts commit b40d943. Reverted pytorch#162001 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
This reverts commit 02c83f1. Reverted pytorch#161999 on behalf of https://github.com/jeanschmidt due to break a few internal tests ([comment](pytorch#161999 (comment)))
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Followup after pytorch#154012 Fixes CPU part of pytorch#160841 Pull Request resolved: pytorch#161999 Approved by: https://github.com/drisspg
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Discovered while debugging pytorch#160841 where sdpa returned NaNs, because during the computation intermediate values were cast back to fp16 before normalization, which was fixed by pytorch#161999 ) Pull Request resolved: pytorch#162401 Approved by: https://github.com/Skylion007, https://github.com/drisspg
dsashidh
pushed a commit
to dsashidh/pytorch
that referenced
this pull request
Sep 26, 2025
Followup after pytorch#154012 Since the introduction of `gemm_no_downcast_stub` it's no longer necessary to allocate temporary array and then manually implement the `beta` logic in the codebase Pull Request resolved: pytorch#162001 Approved by: https://github.com/drisspg ghstack dependencies: pytorch#161999
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.
Stack from ghstack (oldest at bottom):
gemm#162001Followup after #154012
Fixes CPU part of #160841
cc @jianyuh @nikitaved @mruberry @walterddr @xwang233 @lezcano