starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 19:25:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update vendor ggml code to a5bb8ba4 (#13832)

Browse Source 
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
This commit is contained in:
Jeffrey Morgan
2026-02-02 17:31:59 -08:00
committed by GitHub
parent 8f4a008139
commit ef00199fb4
241 changed files with 21271 additions and 5074 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama/patches/0014-graph-memory-reporting-on-failure.patch
View File

@@ -23,7 +23,7 @@ index 78aa059dd..7fa8403b3 100644
// Utils
// Create a buffer and allocate all the tensors in a ggml_context
diff --git a/ggml/include/ggml-backend.h b/ggml/include/ggml-backend.h
index 4ed5f3577..a7ebe5dcd 100644
index a9d177864..393c329be 100644
--- a/ggml/include/ggml-backend.h
+++ b/ggml/include/ggml-backend.h
@@ -319,6 +319,7 @@ extern "C" {
@@ -121,7 +121,7 @@ index 41419b617..73b39bfea 100644
static void free_buffers(ggml_backend_buffer_t ** buffers, const size_t * n_buffers) {
diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp
index 9f37ca70c..1459d16dd 100644
index 9e67c769a..20b37a0b3 100644
--- a/ggml/src/ggml-backend.cpp
+++ b/ggml/src/ggml-backend.cpp
@@ -1859,6 +1859,13 @@ size_t ggml_backend_sched_get_buffer_size(ggml_backend_sched_t sched, ggml_backe