llama : remove quantization sanity check #17788
Merged
+0
−27
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
Member
|
With this patch, Qwen3 Next fails: I think we should just remove this sanity check - it's not really useful anyway. |
This commit removes the quantization sanity check for attention layers. The motivation for this is that there are model that are hybrid models that have recurrent layers, experts layers, and attention layers. For these models the current check fails as the experts layers are not taking into account. After consideration, it was decided that this check is not strictly necessary, and can be removed to allow for more flexible model architectures.
danbev
force-pushed
the
llama-quants-sanity-check-experts
branch
from
e4c5646 to
0ecbb8c
Compare
danbev
changed the title
ggerganov
approved these changes
Dec 6, 2025
JayZenith
pushed a commit
to JayZenith/llama.cpp
that referenced
this pull request
Dec 7, 2025
* llama : remove quantization sanity check This commit removes the quantization sanity check for attention layers. The motivation for this is that there are model that are hybrid models that have recurrent layers, experts layers, and attention layers. For these models the current check fails as the experts layers are not taking into account. After consideration, it was decided that this check is not strictly necessary, and can be removed to allow for more flexible model architectures. * llama : remove unused pruned_attention_w and is_clip_model vars
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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 commit removes the quantization sanity check for attention layers.
The motivation for this is that there are model that are hybrid models
that have recurrent layers, experts layers, and attention layers. For
these models the current check fails as the experts layers are not
taking into account. After consideration, it was decided that this check
is not strictly necessary, and can be removed to allow for more flexible
model architectures.