mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-25 16:08:01 +00:00
ggml update to b7108 (#12992)
* Revert "vulkan: temporary cary of vulkan fixes (#12971)"
This reverts commit 3a9e8e9fd4.
* ggml update to b7087
* fix argsort on metal
* update to b7108
* fix bakllava regression
This model lacks the metadata for the projector type.
* update to b7209
* fix TopK perf
* only build arm code on arm
This commit is contained in:
@@ -8,10 +8,10 @@ Subject: [PATCH] no power throttling win32 with gnuc
|
||||
1 file changed, 1 insertion(+), 1 deletion(-)
|
||||
|
||||
diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
|
||||
index 4b2f8b7bd..046646282 100644
|
||||
index 5be08d6f4..7a0df30c3 100644
|
||||
--- a/ggml/src/ggml-cpu/ggml-cpu.c
|
||||
+++ b/ggml/src/ggml-cpu/ggml-cpu.c
|
||||
@@ -2441,7 +2441,7 @@ static bool ggml_thread_apply_priority(int32_t prio) {
|
||||
@@ -2463,7 +2463,7 @@ static bool ggml_thread_apply_priority(int32_t prio) {
|
||||
// Newer Windows 11 versions aggresively park (offline) CPU cores and often place
|
||||
// all our threads onto the first 4 cores which results in terrible performance with
|
||||
// n_threads > 4
|
||||
|
||||
Reference in New Issue
Block a user