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 b6840 (#12791)

Browse Source
This commit is contained in:
Daniel Hiltgen
2025-11-06 10:19:22 -08:00
committed by GitHub
parent c4ba257c64
commit 544b6739dd
103 changed files with 3644 additions and 1215 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
llama/patches/0015-ggml-Export-GPU-UUIDs.patch
View File

@@ -12,7 +12,7 @@ with tools (e.g. nvidia-smi) and system management libraries (e.g. nvml).
3 files changed, 63 insertions(+), 6 deletions(-)
diff --git a/ggml/include/ggml-backend.h b/ggml/include/ggml-backend.h
index c54ff98b..229bf387 100644
index c54ff98bf..229bf387b 100644
--- a/ggml/include/ggml-backend.h
+++ b/ggml/include/ggml-backend.h
@@ -158,6 +158,7 @@ extern "C" {
@@ -24,7 +24,7 @@ index c54ff98b..229bf387 100644
size_t memory_total;
// device type
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index c0b1e4c1..5b852f69 100644
index aefc6935e..cc201afff 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -183,6 +183,51 @@ static int ggml_cuda_parse_id(char devName[]) {
@@ -110,7 +110,7 @@ index c0b1e4c1..5b852f69 100644
std::string device_name(prop.name);
if (device_name == "NVIDIA GeForce MX450") {
turing_devices_without_mma.push_back({ id, device_name });
@@ -3276,6 +3323,7 @@ struct ggml_backend_cuda_device_context {
@@ -3268,6 +3315,7 @@ struct ggml_backend_cuda_device_context {
std::string name;
std::string description;
std::string pci_bus_id;
@@ -118,7 +118,7 @@ index c0b1e4c1..5b852f69 100644
};
static const char * ggml_backend_cuda_device_get_name(ggml_backend_dev_t dev) {
@@ -3288,6 +3336,11 @@ static const char * ggml_backend_cuda_device_get_description(ggml_backend_dev_t
@@ -3280,6 +3328,11 @@ static const char * ggml_backend_cuda_device_get_description(ggml_backend_dev_t
return ctx->description.c_str();
}
@@ -130,7 +130,7 @@ index c0b1e4c1..5b852f69 100644
static void ggml_backend_cuda_device_get_memory(ggml_backend_dev_t dev, size_t * free, size_t * total) {
ggml_backend_cuda_device_context * ctx = (ggml_backend_cuda_device_context *)dev->context;
ggml_cuda_set_device(ctx->device);
@@ -3304,6 +3357,7 @@ static void ggml_backend_cuda_device_get_props(ggml_backend_dev_t dev, ggml_back
@@ -3296,6 +3349,7 @@ static void ggml_backend_cuda_device_get_props(ggml_backend_dev_t dev, ggml_back
props->name = ggml_backend_cuda_device_get_name(dev);
props->description = ggml_backend_cuda_device_get_description(dev);
@@ -138,7 +138,7 @@ index c0b1e4c1..5b852f69 100644
props->type = ggml_backend_cuda_device_get_type(dev);
props->device_id = ctx->pci_bus_id.empty() ? nullptr : ctx->pci_bus_id.c_str();
ggml_backend_cuda_device_get_memory(dev, &props->memory_free, &props->memory_total);
@@ -3873,6 +3927,7 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
@@ -3869,6 +3923,7 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
cudaDeviceProp prop;
CUDA_CHECK(cudaGetDeviceProperties(&prop, i));
dev_ctx->description = prop.name;
@@ -147,7 +147,7 @@ index c0b1e4c1..5b852f69 100644
char pci_bus_id[16] = {};
snprintf(pci_bus_id, sizeof(pci_bus_id), "%04x:%02x:%02x.0", prop.pciDomainID, prop.pciBusID, prop.pciDeviceID);
diff --git a/ggml/src/ggml-metal/ggml-metal.cpp b/ggml/src/ggml-metal/ggml-metal.cpp
index bf096227..f2ff9f32 100644
index bf0962274..f2ff9f322 100644
--- a/ggml/src/ggml-metal/ggml-metal.cpp
+++ b/ggml/src/ggml-metal/ggml-metal.cpp
@@ -538,6 +538,7 @@ static enum ggml_backend_dev_type ggml_backend_metal_device_get_type(ggml_backen