Fix graph for RWKV6Qwen2 #11445
Merged
Fix graph for RWKV6Qwen2 #11445
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: Molly Sophia <mollysophia379@gmail.com>
Animaxx
added a commit
to Animaxx/llama.cpp
that referenced
this pull request
Jan 28, 2025
slaren
approved these changes
Jan 28, 2025
21 tasks
tinglou
pushed a commit
to tinglou/llama.cpp
that referenced
this pull request
Feb 13, 2025
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
mglambda
pushed a commit
to mglambda/llama.cpp
that referenced
this pull request
Mar 8, 2025
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
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Outdated suggestions cannot be applied.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.
The token-shifting part was not correctly done in the previous implementation. It wasn't copied back to k_cache after a decode. As a result, the model was always lerping towards zero when decoding. Prefill(and as a result, PPL evaluation) wasn't affected.
Somehow this mistake didn't affect much on text generation as well lol (maybe the large 32B model already got enough context information into the wkv state?). That's why the bug wasn't found previously.