mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml update to b7108 (#12992)

Browse Source 
* 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:
Daniel Hiltgen
2025-12-03 19:43:29 -08:00
committed by GitHub
parent 854d40edc5
commit 0cf7794b16
303 changed files with 32711 additions and 23435 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
llama/patches/0029-ggml-cuda-skip-large-batches.patch Normal file
View File

@@ -0,0 +1,25 @@
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 736d47c07..7350f6758 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -4564,6 +4564,9 @@ 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)) {