mirror of
https://github.com/ollama/ollama.git
synced 2025-11-11 04:57:52 +01:00
Llama cpp bump (df1b612): granite docling / mamba2 optimizations / multimodal encoding fixes (#12552)
* feat: Bump llama.cpp to df1b612 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(mtmd): Correctly encode text chunks during mtmd tokenization There can be text chunks that appear interspersed with the image embeddings that contain template delimiter tokens for some models. These need to be correctly translated to text tokens. Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * tests: Use MtmdChunk in image_test Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * style: Fix unnecessary conversion linting Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(ggml): Revert changes to ggml_hip.cpp These changes were done largely by our code assistant and are likely wrong Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Revert changes in mem_nvml.cpp Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update sync point to 1deee0 This brings in several more optimization commits and model support for EmbeddingGemma Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches for 1deee0 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: sync for bump to 1deee0 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Bad patch updates with errant `+` Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Bump llama.cpp/ggml to 7049736 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: format-patches after latest bump Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
GitHub
@@ -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 fe20dca3..48777212 100644
|
||||
index c54ff98b..229bf387 100644
|
||||
--- a/ggml/include/ggml-backend.h
|
||||
+++ b/ggml/include/ggml-backend.h
|
||||
@@ -158,6 +158,7 @@ extern "C" {
|
||||
@@ -24,7 +24,7 @@ index fe20dca3..48777212 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 fdf8c63d..ad389ece 100644
|
||||
index c0b1e4c1..5b852f69 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 fdf8c63d..ad389ece 100644
|
||||
std::string device_name(prop.name);
|
||||
if (device_name == "NVIDIA GeForce MX450") {
|
||||
turing_devices_without_mma.push_back({ id, device_name });
|
||||
@@ -3273,6 +3320,7 @@ struct ggml_backend_cuda_device_context {
|
||||
@@ -3276,6 +3323,7 @@ struct ggml_backend_cuda_device_context {
|
||||
std::string name;
|
||||
std::string description;
|
||||
std::string pci_bus_id;
|
||||
@@ -118,7 +118,7 @@ index fdf8c63d..ad389ece 100644
|
||||
};
|
||||
|
||||
static const char * ggml_backend_cuda_device_get_name(ggml_backend_dev_t dev) {
|
||||
@@ -3285,6 +3333,11 @@ static const char * ggml_backend_cuda_device_get_description(ggml_backend_dev_t
|
||||
@@ -3288,6 +3336,11 @@ static const char * ggml_backend_cuda_device_get_description(ggml_backend_dev_t
|
||||
return ctx->description.c_str();
|
||||
}
|
||||
|
||||
@@ -130,7 +130,7 @@ index fdf8c63d..ad389ece 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);
|
||||
@@ -3301,6 +3354,7 @@ static void ggml_backend_cuda_device_get_props(ggml_backend_dev_t dev, ggml_back
|
||||
@@ -3304,6 +3357,7 @@ 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 fdf8c63d..ad389ece 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);
|
||||
@@ -3871,6 +3925,7 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
|
||||
@@ -3873,6 +3927,7 @@ 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 fdf8c63d..ad389ece 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 909e17de..08ab4fc9 100644
|
||||
index bf096227..f2ff9f32 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
|
||||
|
||||
Reference in New Issue
Block a user