Fix hordeconfig max context setting, and add Makefile flags for cuda F16/KQuants per iter.#252
Merged
LostRuins merged 2 commits intoLostRuins:concedofrom Jun 21, 2023
Merged
Conversation
ycros
changed the title
|
Sometimes the speed of this makes my head spin. Saw this issue last night, figured I'd start to work on when I got a free minute today, turns out ycros already did the work by the time I got there. Dropped a comment in the upstream issue (ggml-org#1862 (comment)_) as well. Might be worth documenting on the koboldcpp page regarding compile flags, given LLAMA_CUDA_KQUANTS_ITER=1 has a pretty drastic impact on those of us running the pascal architecture (almost exactly 2x slower inference for 2k and 6k quant types). |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Makefile flags are copied right from llama.cpp's Makefile.