matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-20 04:37:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

add new gemma model (#11204)

Browse Source 
* update patches

* cherry pick metal mean kernel

* cherry pick cuda mean kernel

* gemma3n
This commit is contained in:
Michael Yang
2025-06-25 21:47:09 -07:00
committed by GitHub
parent ad118d8b13
commit 73b642e6f3
25 changed files with 6084 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama/patches/0005-solar-pro.patch
View File

@@ -150,7 +150,7 @@ index 4cce5166..7f6617fa 100644
llama_model_loader::llama_model_loader(
const std::string & fname,
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 3a4e72a3..831b68c0 100644
index 3a4e72a3..db62973f 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1402,6 +1402,21 @@ void llama_model::load_hparams(llama_model_loader & ml) {