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:
#	.devops/tools.sh
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.github/workflows/server.yml
#	Makefile
#	README.md
#	cmake/llama-config.cmake.in
#	common/CMakeLists.txt
#	examples/gbnf-validator/gbnf-validator.cpp
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/server/tests/README.md
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-grammar-integration.cpp
This commit is contained in:
Concedo 2025-02-01 17:14:59 +08:00
commit f13498df13
75 changed files with 1257924 additions and 701572 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ggml/src/ggml-cpu/ggml-cpu.c
View file

@ -1306,7 +1306,7 @@ struct ggml_threadpool {
// these are atomic as an annotation for thread-sanitizer
atomic_bool stop; // Used for stopping the threadpool altogether
atomic_bool pause; // Used for pausing the threadpool or individual threads
atomic_bool abort; // Used for aborting processing of a graph
atomic_int abort; // Used for aborting processing of a graph
struct ggml_compute_state * workers; // per thread state
int n_threads_max; // number of threads in the pool
@ -13895,14 +13895,14 @@ static thread_ret_t ggml_graph_compute_thread(void * data) {
/*.threadpool=*/ tp,
};
for (int node_n = 0; node_n < cgraph->n_nodes && !tp->abort; node_n++) {
for (int node_n = 0; node_n < cgraph->n_nodes && atomic_load_explicit(&tp->abort, memory_order_relaxed) != node_n; node_n++) {
struct ggml_tensor * node = cgraph->nodes[node_n];
ggml_compute_forward(&params, node);
if (state->ith == 0 && cplan->abort_callback &&
cplan->abort_callback(cplan->abort_callback_data)) {
tp->abort = true;
atomic_store_explicit(&tp->abort, node_n + 1, memory_order_relaxed);
tp->ec = GGML_STATUS_ABORTED;
}
@ -14075,7 +14075,7 @@ static struct ggml_threadpool * ggml_threadpool_new_impl(
threadpool->current_chunk = 0;
threadpool->stop = false;
threadpool->pause = tpp->paused;
threadpool->abort = false;
threadpool->abort = -1;
threadpool->workers = NULL;
threadpool->n_threads_max = tpp->n_threads;
threadpool->n_threads_cur = tpp->n_threads;
@ -14154,7 +14154,7 @@ enum ggml_status ggml_graph_compute(struct ggml_cgraph * cgraph, struct ggml_cpl
threadpool->cgraph = cgraph;
threadpool->cplan = cplan;
threadpool->current_chunk = 0;
threadpool->abort = false;
threadpool->abort = -1;
threadpool->ec = GGML_STATUS_SUCCESS;
}