mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 14:26:30 +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
1.1 KiB
Diff
26 lines
1.1 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Michael Yang <git@mxy.ng>
|
|
Date: Tue, 18 Nov 2025 11:13:04 -0800
|
|
Subject: [PATCH] ggml-cuda: skip large batches
|
|
|
|
cuda panics on batches larger than 1024 so mark it as unsupported to
|
|
fallback to cpu
|
|
---
|
|
ggml/src/ggml-cuda/ggml-cuda.cu | 3 +++
|
|
1 file changed, 3 insertions(+)
|
|
|
|
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
|
|
index cd71902df..d69d62193 100644
|
|
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
|
|
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
|
|
@@ -4632,6 +4632,9 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
|
|
if (b->type == GGML_TYPE_F16 && a->type != GGML_TYPE_F16) {
|
|
return false;
|
|
}
|
|
+ if (op->op == GGML_OP_MUL_MAT && b->ne[2] * b->ne[3] > 1024) {
|
|
+ return false;
|
|
+ }
|
|
#ifdef GGML_USE_MUSA
|
|
const int cc = ggml_cuda_info().devices[dev_ctx->device].cc;
|
|
if (b->ne[2]*b->ne[3] > 1 && !ggml_is_transposed(a) && !ggml_is_transposed(b)) {
|