Repository navigation
Conversation
This is a small shim that vendors the header-only API from the latest Torch. We always build stable ABI kernels with the latest Torch version that supports a given backend version. However, in some cases this leads to the use of older Torch versions (e.g. Torch 2.11 for CUDA 12.8), which do not have the latest header-only API. If a kernel needs a newer API, depend on the shim to get these newer headers, even on older Torch versions. We might also use the shim in the future for our own functions that are compatible with the stable ABI, but are more efficient than the upstream counterparts (e.g. because they go through the dispatcher).
Coverage report —
|
| Name | Stmts | Miss | Cover | Missing |
|---|---|---|---|---|
| src/kernels/__init__.py | 14 | 0 | 100% | |
| src/kernels/_system.py | 6 | 1 | 83% | 10 |
| src/kernels/_versions.py | 130 | 14 | 89% | 53, 59-60, 63-64, 102, 165-170, 199, 219 |
| src/kernels/archs.py | 56 | 1 | 98% | 94 |
| src/kernels/backends.py | 215 | 63 | 71% | 42, 46, 50-53, 70, 92, 110, 119, 123, 127-129, 150, 159, 163, 167-169, 190, 201, 203, 210-213, 222, 226, 230-255, 263, 286-306 |
| src/kernels/compat.py | 9 | 1 | 89% | 5 |
| src/kernels/deps.py | 70 | 1 | 99% | 56 |
| src/kernels/hf_hub.py | 63 | 2 | 97% | 21, 23 |
| src/kernels/importer.py | 50 | 5 | 90% | 95, 99, 102, 116-117 |
| src/kernels/install.py | 21 | 7 | 67% | 76-100 |
| src/kernels/layer/__init__.py | 6 | 0 | 100% | |
| src/kernels/layer/_interval_tree.py | 103 | 4 | 96% | 23, 52, 147, 150 |
| src/kernels/layer/device.py | 48 | 14 | 71% | 42, 47-49, 91, 96-98, 101, 149, 152, 155-157 |
| src/kernels/layer/func.py | 85 | 6 | 93% | 90, 115, 191, 311, 338, 368 |
| src/kernels/layer/globals.py | 5 | 0 | 100% | |
| src/kernels/layer/kernelize.py | 82 | 8 | 90% | 259, 297, 305-306, 312, 316, 332-334 |
| src/kernels/layer/layer.py | 309 | 15 | 95% | 211, 258, 285, 416, 556-557, 578, 586, 597, 637, 641, 654, 708, 738, 813 |
| src/kernels/layer/mode.py | 14 | 0 | 100% | |
| src/kernels/layer/repos.py | 144 | 42 | 71% | 27, 33, 36-43, 63-64, 70, 73-76, 90, 94, 103-104, 110, 113-116, 123-124, 130, 133-136, 143-144, 150, 153-156, 163-164, 170, 173-176, 257 |
| src/kernels/load.py | 71 | 2 | 97% | 338, 378 |
| src/kernels/locking.py | 89 | 64 | 28% | 35-83, 91-98, 102-125, 137, 152-159, 165-175, 179-186 |
| src/kernels/python_deps.py | 58 | 6 | 90% | 59-60, 64-65, 101, 104 |
| src/kernels/resolver.py | 162 | 1 | 99% | 248 |
| src/kernels/status.py | 50 | 2 | 96% | 25, 79 |
| src/kernels/validate.py | 88 | 5 | 94% | 9, 100, 167, 190-191 |
| src/kernels/variants.py | 278 | 17 | 94% | 65, 96, 117, 147, 256-257, 299-302, 304, 388-394, 400-406, 455-461 |
| src/kernels/verify.py | 127 | 6 | 95% | 46, 202-204, 318-319 |
| TOTAL | 2353 | 287 | 88% |
Updated by the Test kernels workflow on commit e36846758de2ad62e1456ab3e5479d1ab34529d1.
danieldk
marked this pull request as ready for review
October 20, 2026 14:50
danieldk
commented
Oct 20, 2026
| /// @param dim The dimension to index along. | ||
| /// @param index A 1-D tensor of indices to select. | ||
| /// @return A tensor with values selected along dim. | ||
| inline torch::stable::Tensor index_select( |
Member
Author
There was a problem hiding this comment.
Not 100% sure if we want to add on a case-by-case basis, but that may be annoying for downstream users. So for now I added the complete header (with namespacing changes).
drbh
approved these changes
Oct 20, 2026
drbh
left a comment
drbh
left a comment
Collaborator
There was a problem hiding this comment.
nice!
We might also use the shim in the future for our own functions that are compatible with the stable ABI, but are more efficient than the upstream counterparts (e.g. because they go through the dispatcher).
and great idea to keep things in one location - i'll look into moving some of the fast paths currently in the fa2 pr into the shared shim after this lands
This branch has not been deployed
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.
This is a small shim that vendors the header-only API from the latest Torch.
We always build stable ABI kernels with the latest Torch version that supports a given backend version. However, in some cases this leads to the use of older Torch versions (e.g. Torch 2.11 for CUDA 12.8), which do not have the latest header-only API. If a kernel needs a newer API, depend on the shim to get these newer headers, even on older Torch versions.
We might also use the shim in the future for our own functions that are compatible with the stable ABI, but are more efficient than the upstream counterparts (e.g. because they go through the dispatcher).