vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	examples/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/llama-bench/llama-bench.cpp
#	examples/server/README.md
#	examples/server/server.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/simple/simple.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-amx/CMakeLists.txt
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-kompute/CMakeLists.txt
#	ggml/src/ggml-kompute/ggml-kompute.cpp
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	pocs/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo 2024-11-26 17:01:20 +08:00
commit ec581b19d8
31 changed files with 1383 additions and 676 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/main/main.cpp
View file

@ -166,6 +166,10 @@ int main(int argc, char ** argv) {
LOG_INF("%s: llama threadpool init, n_threads = %d\n", __func__, (int) params.cpuparams.n_threads);
auto * reg = ggml_backend_dev_backend_reg(ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU));
auto * ggml_threadpool_new_fn = (decltype(ggml_threadpool_new) *) ggml_backend_reg_get_proc_address(reg, "ggml_threadpool_new");
auto * ggml_threadpool_free_fn = (decltype(ggml_threadpool_free) *) ggml_backend_reg_get_proc_address(reg, "ggml_threadpool_free");
struct ggml_threadpool_params tpp_batch =
ggml_threadpool_params_from_cpu_params(params.cpuparams_batch);
struct ggml_threadpool_params tpp =
@ -175,7 +179,7 @@ int main(int argc, char ** argv) {
struct ggml_threadpool * threadpool_batch = NULL;
if (!ggml_threadpool_params_match(&tpp, &tpp_batch)) {
threadpool_batch = ggml_threadpool_new(&tpp_batch);
threadpool_batch = ggml_threadpool_new_fn(&tpp_batch);
if (!threadpool_batch) {
LOG_ERR("%s: batch threadpool create failed : n_threads %d\n", __func__, tpp_batch.n_threads);
return 1;
@ -185,7 +189,7 @@ int main(int argc, char ** argv) {
tpp.paused = true;
}
struct ggml_threadpool * threadpool = ggml_threadpool_new(&tpp);
struct ggml_threadpool * threadpool = ggml_threadpool_new_fn(&tpp);
if (!threadpool) {
LOG_ERR("%s: threadpool create failed : n_threads %d\n", __func__, tpp.n_threads);
return 1;
@ -891,8 +895,8 @@ int main(int argc, char ** argv) {
llama_backend_free();
ggml_threadpool_free(threadpool);
ggml_threadpool_free(threadpool_batch);
ggml_threadpool_free_fn(threadpool);
ggml_threadpool_free_fn(threadpool_batch);
return 0;
}