vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-12 18:05:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	docs/BLIS.md
#	flake.lock
#	grammars/README.md
This commit is contained in:
Concedo 2024-05-08 09:58:23 +08:00
commit bc39b4d98a
15 changed files with 94 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/HOWTO-add-model.md
View file

@ -96,9 +96,9 @@ NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorc
This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `llama_build_graph`.
Have a look to existing implementation like `build_llama`, `build_dbrx` or `build_bert`.
Have a look at existing implementation like `build_llama`, `build_dbrx` or `build_bert`.
When implementing a new graph, please note that the underlying `ggml` backends might not support them all, support of missing backend operations can be added in another PR.
When implementing a new graph, please note that the underlying `ggml` backends might not support them all, support for missing backend operations can be added in another PR.
Note: to debug the inference graph: you can use [eval-callback](../examples/eval-callback).