Harden KV Cache qparams #262
Draft
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
Signed-off-by: Kyle Sayers <[email protected]>
Signed-off-by: Kyle Sayers <[email protected]>
…_kv_initialization
Signed-off-by: Kyle Sayers <[email protected]>
…_kv_initialization
horheynm
previously approved these changes
Feb 26, 2025
rahul-tuli
previously approved these changes
Feb 27, 2025
|
|
||
| expected_shape = 1 # per tensor | ||
|
|
||
| param = next(module.parameters()) |
There was a problem hiding this comment.
WHAAAAAAAAAAAAAAT 😨 we just assumed next(model.parameters()) give us the weight param
There was a problem hiding this comment.
Sorry this needs to be reworked. This is meant to be called on an "attention" module, so we need to get the k_proj and v_proj attributes, not the weight attribute.
But yes, making any assumption of ordering on module.parameters() is incorrect
brian-dellabetta
previously approved these changes
Feb 27, 2025
dsikka
dismissed stale reviews from brian-dellabetta, rahul-tuli, and horheynm
The base branch was changed.
rahul-tuli
reviewed
Apr 30, 2025
| param = next(module.parameters()) | ||
| scale_dtype = param.dtype | ||
| device = param.device | ||
| weight_param = getattr(module, "weight", next(module.parameters())) |
There was a problem hiding this comment.
Should this be q_proj weights?
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Outdated suggestions cannot be applied.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.
Purpose
parameters()is not the weightPrerequisites