add python/pytorch version compat notes #44
Merged
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
44670
pushed a commit
to 44670/llama.cpp
that referenced
this pull request
Aug 2, 2023
* RAM usage reduction and calculations Removed -b batch limit (1024) (tested up to-b 8192) Fixed a integer overflow in ggml matmul (happened at around nbatch 3000) Added a dynamic calculation for batched scratch memory consumption Overall reduced RAM buffer sizes by magnitudes for normal settings RAM usage scales quadratically with increasing context size * batch Using a small batch (or default 1) will result in a very small memory footprint even at thousands of tokens processed Tested up to 13,000 tokens prompt and 8k batch Needs more tests on various platforms * removed debug * minor ---------
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Outdated suggestions cannot be applied.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.
see #32 (comments)