Conversation
Pull Request resolved: #10525 ## Context When quantizing models with the PT2E quantization flow, quantize/dequantize nodes will be inserted into the graph. However, these quantize/dequantize nodes must be fused with operators such as `aten.linear.default` to produce nodes corresponding to quantized operators (e.g. `weight_int8pack_mm`) in order for quantized operator implementations to be called at runtime. Currently, the op fusion is done by the `fuse_dequant_linear.py` pass, however, this only handles one specific fusion pattern to generate a `weight_int8pack_mm` operator. As more quantized operators are to be supported in ET-VK via the PT2E quantization flow, a more generic fusion pass is needed that can handle a variety of fusion patterns. ## Changes Introduce the `FuseQuantizedOpsTransform()` pass. I elected to introduce a new pass under the `backends/vulkan/_passes` directory, as opposed to modifying the existing pass because I anticipate the majority of the fusion patterns to be specific to ET-VK. Remove the existing `FuseDequantLinearPass()` Switch to using the `FuseQuantizedOpsTransform` pass instead of the old `FuseDequantLinear` pass. Add `test_vulkan_passes` Python test to test export passes. Added some refactors to `test_vulkan_delegate` Python test to improve code organization. Introduce the `linear_qcsnw` nomenclature: * q - quantized * c - per-channel / channelswise * s - symmetric * n - number of bits (qcs4w for 4-bit quant, qcs8w for 8-bit quant) * w - weight quantized Added custom op for `linear_qcs4w` for 4-bit weight quantized linear and add the ability for the quantized op fusion pass to produce this op. Slight renaming/refactoring of quantization config retrieval functions in the `VulkanQuantizer` to improve clarity and API flexibility. ghstack-source-id: 282688199 @exported-using-ghexport Differential Revision: [D73794042](https://our.internmc.facebook.com/intern/diff/D73794042/)
Pull Request resolved: #10588 ## Context Title says it all! ## Changes Extended the implementation of `linear_qcsnw` to support packed 4-bit weight tensors. ghstack-source-id: 282707610 @exported-using-ghexport Differential Revision: [D73941991](https://our.internmc.facebook.com/intern/diff/D73941991/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10772
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. |
facebook-github-bot
added
the
CLA Signed
SS-JIA
requested review from
iseeyuan,
jackzhxng,
kimishpatel,
larryliu0820 and
swolchok
as code owners
SS-JIA
approved these changes
May 8, 2025
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 PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #10588 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/222/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/222/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/220/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/222/orig
@diff-train-skip-merge