Optimize attention output linear fp8 memory #10204
Merged
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
|
Thanks for your contribution! |
sneaxiy
approved these changes
Mar 19, 2025
lixinqi
reviewed
Mar 19, 2025
| x_quant, x_scale = kitchen_quant( | ||
| x, backend=kitchen.ops.Backend.CUTLASS, is_1d_scaled=True, return_transpose=False | ||
| ) | ||
| weight_t = weight.T.contiguous() |
lixinqi
reviewed
Mar 19, 2025
| ) | ||
|
|
||
|
|
||
| x_t_shape = x_t_shape.numpy() |
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Outdated suggestions cannot be applied.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.
output linear的输入 x ，是fa的输出，这个变量，在fa反向的时候是需要的，所以在output linear 使用fp的时候，save for backward可以直接用x，用x_fp8 会增加显存；单层decoder 大约能节省100M空间