[ZENDNN] Adding support for slice in opaque #3494
Open
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/pytorch/ao/3494
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
jerryzh168
reviewed
Dec 18, 2025
| block_size = list(self.block_size) | ||
| block_size[dim] = min(block_size[dim], new_shape[dim]) | ||
|
|
||
| return Int4TilePackedTo4dTensor( |
Author
There was a problem hiding this comment.
I accidentally committed the incorrect changes; they’re resolved now.
Priyjain-amd
force-pushed
the
slice_support_opaque
branch
from
391af1b to
2853956
Compare
- Issue pytorch#3499 Signed-off-by: priyansh jain <[email protected]> Change-Id: I0b2cb105c5eacdd251d159ae5f007b2118bb9ce7
Priyjain-amd
force-pushed
the
slice_support_opaque
branch
from
2853956 to
7157706
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Add support
Int4OpaqueTensorfrom torchao in vLLM's LLaMA model implementation.These changes enable vLLM to load models quantized with
torchaousingint4_packing_format="opaque"without errors during weight loading.Encountered error: NotImplementedError: Int4OpaqueTensor dispatch: attempting to run unimplemented operator/function:
func=<OpOverload(op='aten.slice', overload='Tensor')>
Issue #3499