RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list #9387
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
Signed-off-by: Molly Sophia <[email protected]>
ggerganov
approved these changes
Sep 9, 2024
|
@MollySophia can add time_maa_w1 time_maa_w2 to exclusion list too? and f16 is enough |
compilade
approved these changes
Sep 9, 2024
These two are already there :D |
dsx1986
pushed a commit
to dsx1986/llama.cpp
that referenced
this pull request
Oct 29, 2024
…9387) Signed-off-by: Molly Sophia <[email protected]>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
…9387) Signed-off-by: Molly Sophia <[email protected]>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
…9387) Signed-off-by: Molly Sophia <[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Outdated suggestions cannot be applied.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.
This seems to be a mistake that wasn't discovered in the initial PR.
The time_decay operations in RWKV v6 is pretty sensitive (since it's done recursively many times during the sequence). It's better keeps these related weights unquantized.