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>
26 lines
1.0 KiB
Diff
26 lines
1.0 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Daniel Hiltgen <daniel@ollama.com>
|
|
Date: Tue, 11 Nov 2025 11:39:43 -0800
|
|
Subject: [PATCH] fix bakllava regression
|
|
|
|
Rever to prior logic of assuming an empty projector type is mlp
|
|
---
|
|
tools/mtmd/clip.cpp | 4 ++++
|
|
1 file changed, 4 insertions(+)
|
|
|
|
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
|
|
index 6be1470ad..2a325c726 100644
|
|
--- a/tools/mtmd/clip.cpp
|
|
+++ b/tools/mtmd/clip.cpp
|
|
@@ -2649,6 +2649,10 @@ struct clip_model_loader {
|
|
if (proj_type.empty()) {
|
|
if (modality == CLIP_MODALITY_VISION) {
|
|
get_string(KEY_VISION_PROJ_TYPE, proj_type, false);
|
|
+ if (proj_type.empty()) {
|
|
+ // Assume MLP if no projector type listed
|
|
+ proj_type = "mlp";
|
|
+ }
|
|
} else if (modality == CLIP_MODALITY_AUDIO) {
|
|
get_string(KEY_AUDIO_PROJ_TYPE, proj_type, false);
|
|
} else {
|