-
Notifications
You must be signed in to change notification settings - Fork 8.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Skip computation of much of last layer & unused logits during prompt eval / large N #2700
Closed
Commits on Aug 24, 2023
-
Skip computation of unused logits during batch prompt eval (drop othe…
…r batch positions after writing their kv to cache)
Configuration menu - View commit details
-
Copy full SHA for 2cf4f62 - Browse repository at this point
Copy the full SHA 2cf4f62View commit details -
Configuration menu - View commit details
-
Copy full SHA for 7ec7ef9 - Browse repository at this point
Copy the full SHA 7ec7ef9View commit details
Commits on Aug 25, 2023
-
Allow disabling unused logit skipping code w/ cmake / make options
cmake -DLLAMA_SKIP_UNUSED_LOGITS=OFF ... LLAMA_NO_SKIP_UNUSED_LOGITS=1 make ...
Configuration menu - View commit details
-
Copy full SHA for 5553820 - Browse repository at this point
Copy the full SHA 5553820View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3be6e8d - Browse repository at this point
Copy the full SHA 3be6e8dView commit details -
Configuration menu - View commit details
-
Copy full SHA for e23fa92 - Browse repository at this point
Copy the full SHA e23fa92View commit details
Commits on Aug 27, 2023
-
Configuration menu - View commit details
-
Copy full SHA for 21df40d - Browse repository at this point
Copy the full SHA 21df40dView commit details
Commits on Aug 28, 2023
-
Configuration menu - View commit details
-
Copy full SHA for 2eaeb7e - Browse repository at this point
Copy the full SHA 2eaeb7eView commit details -
Configuration menu - View commit details
-
Copy full SHA for f6a446e - Browse repository at this point
Copy the full SHA f6a446eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 9f5b781 - Browse repository at this point
Copy the full SHA 9f5b781View commit details -
Configuration menu - View commit details
-
Copy full SHA for e9e8ac4 - Browse repository at this point
Copy the full SHA e9e8ac4View commit details
Commits on Aug 30, 2023
-
Configuration menu - View commit details
-
Copy full SHA for d547e05 - Browse repository at this point
Copy the full SHA d547e05View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4974f37 - Browse repository at this point
Copy the full SHA 4974f37View commit details
Commits on Sep 11, 2023
-
Configuration menu - View commit details
-
Copy full SHA for 646caf9 - Browse repository at this point
Copy the full SHA 646caf9View commit details
Commits on Sep 20, 2023
-
Configuration menu - View commit details
-
Copy full SHA for 55d49b2 - Browse repository at this point
Copy the full SHA 55d49b2View commit details -
Makefile: move unused logits flags where they don't interfere w/ targets
(and also fix bad merge)
Configuration menu - View commit details
-
Copy full SHA for 58bb7d5 - Browse repository at this point
Copy the full SHA 58bb7d5View commit details
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.