Make WeightOnlyInt8QuantLinear more compatible with torch.compile #19
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
facebook-github-bot
added
the
CLA Signed
|
may be good to align the forward method with the tensor subclass as well. |
HDCharles
reviewed
Dec 5, 2023
| ) | ||
| new_mod.register_buffer("w_int8", w_int8.t()) | ||
| new_mod.scales = torch.nn.Parameter(scales) |
There was a problem hiding this comment.
probably want requires_grad = False
jerryzh168
pushed a commit
that referenced
this pull request
Sep 18, 2024
* Bring `torch.compile` to `quant_block_v2_`. (#18) Signed-off-by: yiliu30 <[email protected]> * Add `AO_USE_DETERMINISTIC_ALGORITHMS` for reproducing results (#19) Signed-off-by: yiliu30 <[email protected]> * Add `gradient_accumulate_steps` and update results (#20) Signed-off-by: yiliu30 <[email protected]> * update the readme Signed-off-by: yiliu30 <[email protected]> * udpate Signed-off-by: yiliu30 <[email protected]> * update the desc Signed-off-by: yiliu30 <[email protected]> * rename `train_bs` to `batch_size` Signed-off-by: yiliu30 <[email protected]> * update the eval Signed-off-by: yiliu30 <[email protected]> * update Signed-off-by: yiliu30 <[email protected]> --------- Signed-off-by: yiliu30 <[email protected]>
jainapurva
pushed a commit
that referenced
this pull request
Sep 22, 2024
* Bring `torch.compile` to `quant_block_v2_`. (#18) Signed-off-by: yiliu30 <[email protected]> * Add `AO_USE_DETERMINISTIC_ALGORITHMS` for reproducing results (#19) Signed-off-by: yiliu30 <[email protected]> * Add `gradient_accumulate_steps` and update results (#20) Signed-off-by: yiliu30 <[email protected]> * update the readme Signed-off-by: yiliu30 <[email protected]> * udpate Signed-off-by: yiliu30 <[email protected]> * update the desc Signed-off-by: yiliu30 <[email protected]> * rename `train_bs` to `batch_size` Signed-off-by: yiliu30 <[email protected]> * update the eval Signed-off-by: yiliu30 <[email protected]> * update Signed-off-by: yiliu30 <[email protected]> --------- Signed-off-by: yiliu30 <[email protected]>
jainapurva
pushed a commit
that referenced
this pull request
Sep 23, 2024
* Bring `torch.compile` to `quant_block_v2_`. (#18) Signed-off-by: yiliu30 <[email protected]> * Add `AO_USE_DETERMINISTIC_ALGORITHMS` for reproducing results (#19) Signed-off-by: yiliu30 <[email protected]> * Add `gradient_accumulate_steps` and update results (#20) Signed-off-by: yiliu30 <[email protected]> * update the readme Signed-off-by: yiliu30 <[email protected]> * udpate Signed-off-by: yiliu30 <[email protected]> * update the desc Signed-off-by: yiliu30 <[email protected]> * rename `train_bs` to `batch_size` Signed-off-by: yiliu30 <[email protected]> * update the eval Signed-off-by: yiliu30 <[email protected]> * update Signed-off-by: yiliu30 <[email protected]> --------- Signed-off-by: yiliu30 <[email protected]>
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.
No description provided.