vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-intel.Dockerfile
#	.devops/llama-cli-musa.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-musa.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	cmake/llama-config.cmake.in
#	docs/backend/SYCL.md
#	docs/build.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-11-21 16:26:24 +08:00
commit 091a432cf6
38 changed files with 167475 additions and 136736 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-backend.cpp
View file

@ -252,6 +252,7 @@ void ggml_backend_tensor_get_async(ggml_backend_t backend, const struct ggml_ten
}
void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void * data, size_t offset, size_t size) {
GGML_ASSERT(tensor);
ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
if (size == 0) {
@ -266,6 +267,7 @@ void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void * data, siz
}
void ggml_backend_tensor_get(const struct ggml_tensor * tensor, void * data, size_t offset, size_t size) {
GGML_ASSERT(tensor);
ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
if (size == 0) {
@ -689,7 +691,7 @@ static int ggml_backend_sched_backend_id(ggml_backend_sched_t sched, ggml_backen
}
static int ggml_backend_sched_backend_from_buffer(ggml_backend_sched_t sched, const struct ggml_tensor * tensor, const struct ggml_tensor * op) {
ggml_backend_buffer_t buffer = tensor->buffer;
ggml_backend_buffer_t buffer = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
if (buffer == NULL) {
return -1;
}
@ -724,8 +726,6 @@ static bool backend_prealloc_warn = false;
// returns the backend that should be used for the node based on the current locations
static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, struct ggml_tensor * tensor) {
// TODO: use supports_op to check if the backend supports the op
// assign pre-allocated nodes to their backend
int cur_backend_id = ggml_backend_sched_backend_from_buffer(sched, tensor, tensor);
if (cur_backend_id != -1) {
@ -747,7 +747,7 @@ static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, st
if(!backend_prealloc_warn)
{
backend_prealloc_warn = true;
printf("\nCaution: pre-allocated tensor in a backend that cannot run the operation\n");
printf("\nCaution: pre-allocated tensor (%s) in a backend that cannot run the operation\n", tensor->name);
}
}