update SqueezeInt4LinearInputs to process relu/gelu inputs too #8601
Conversation
This file contains 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/executorch/8601
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 889448b with merge base 254eeca ( BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D69673068 |
…ch#8601) Summary: Update/rename SqueezeInt4LinearInputs pass so it wraps gelu/relu with squeeze/unsqueeze view ops too Differential Revision: D69673068
jorgep31415
approved these changes
Feb 20, 2025
nathanaelsee
force-pushed
the
export-D69673068
branch
from
90c24a8 to
889448b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69673068 |
nathanaelsee
added
the
release notes: vulkan
SS-JIA
added a commit
that referenced
this pull request
Apr 4, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 4, 2025
…ments more strict" ## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 4, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 7, 2025
…ments more strict" ## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 7, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 7, 2025
…ments more strict" ## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 7, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/) [ghstack-poisoned]
kirklandsign
pushed a commit
that referenced
this pull request
Apr 7, 2025
Pull Request resolved: #9917 ## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. ghstack-source-id: 276566115 @exported-using-ghexport Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/)
kirklandsign
pushed a commit
that referenced
this pull request
Apr 7, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/)
kirklandsign
pushed a commit
that referenced
this pull request
Apr 11, 2025
## Context Refactor the `SqueezeUnsqueezeInputs` pass to be more clear about its intention. For Llama models, input shapes to 4 bit linear will oftentimes have the shape `[1, seq_len, dim]`; under the current implementation of the pass, the input would be squeezed to `[seq_len, dim]` even though the squeeze is not necessary. The original intention of thispass was to squeeze inputs with shape `[batch_size, 1, dim]` to `[batch_size, dim]` before calling the 4-bit linear operator. ## Changes To avoid inserting unnecessary squeeze/unsqueezes, be more specific about when squeeze/unsqueeze should be added. I would like to consider refactoring this pass in the future, since the logic is currently a bit uninttuitive. Squeeze/unsqueeze is also inserted for gelu and relu, but this is to create a chain of unsqueeze/squeeze that will be eliminated by a later pass (see #8601 / D69673068). I think eventually it will be good to rewrite the pass to make shape management more explicit and self contained within the pass rather than inserting ops which are expected to be removed later on. Differential Revision: [D72480178](https://our.internmc.facebook.com/intern/diff/D72480178/)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary: Update/rename SqueezeInt4LinearInputs pass so it wraps gelu/relu with squeeze/unsqueeze view ops too
Differential Revision: D69673068