matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-19 04:07:01 +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

6
llama/patches/0008-ensure-KV-cache-is-fully-defragmented.patch
View File

@@ -22,10 +22,10 @@ multiple batches of processing until everything is complete.
4 files changed, 59 insertions(+), 79 deletions(-)
diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index c22687e4..c5948e8f 100644
index dca22d8b..1f3a3956 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -950,9 +950,12 @@ int llama_context::decode(llama_batch & inp_batch) {
@@ -947,9 +947,12 @@ int llama_context::decode(llama_batch & inp_batch) {
// find KV slot
if (!kv_self->find_slot(ubatch)) {
@@ -41,7 +41,7 @@ index c22687e4..c5948e8f 100644
}
ggml_backend_sched_reset(sched.get());
@@ -1967,9 +1970,12 @@ void llama_context::opt_epoch_iter(
@@ -1965,9 +1968,12 @@ void llama_context::opt_epoch_iter(
// TODO: not sure if this is needed
if (!kv_self->find_slot(ubatch)) {