mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 22:33:56 +00:00
b95693056c
* feat: Bump llama.cpp to the latest master (17f7f4b) This brings in significant improvements to prefill performance for all models using the SSM_CONV and SSM_SCAN ops (granite4, jamba, falcon-h, nemotron-h, Qwen3 Next) on Apple Metal. See https://github.com/ggml-org/llama.cpp/pull/17876 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 1-4 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Update patches 5-12 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 13-18 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patch 20 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 21-31 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Sync vendored code The two files I'm not sure about here are the swap from gemma3-iswa.cpp to gemma3.cpp (I chose to include this because I think it's required), and the inclusion of `ggml-zendnn.h` which I chose to omit. Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
29 lines
764 B
Diff
29 lines
764 B
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Daniel Hiltgen <daniel@ollama.com>
|
|
Date: Tue, 18 Nov 2025 09:58:23 -0800
|
|
Subject: [PATCH] win: exit instead of abort
|
|
|
|
---
|
|
ggml/src/ggml.c | 7 ++++++-
|
|
1 file changed, 6 insertions(+), 1 deletion(-)
|
|
|
|
diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c
|
|
index 530ff7b95..fc0196eb7 100644
|
|
--- a/ggml/src/ggml.c
|
|
+++ b/ggml/src/ggml.c
|
|
@@ -250,8 +250,13 @@ void ggml_abort(const char * file, int line, const char * fmt, ...) {
|
|
fprintf(stderr, "%s\n", message);
|
|
ggml_print_backtrace();
|
|
}
|
|
-
|
|
+#if defined(_WIN32)
|
|
+ fflush(stderr);
|
|
+ fflush(stdout);
|
|
+ exit(1);
|
|
+#else
|
|
abort();
|
|
+#endif
|
|
}
|
|
|
|
// ggml_print_backtrace is registered with std::set_terminate by ggml.cpp
|