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

23
ggml/src/ggml-cpu/ggml-cpu.c
View file

@ -13619,29 +13619,6 @@ static void ggml_graph_compute_kickoff(struct ggml_threadpool * threadpool, int
#endif // GGML_USE_OPENMP
void ggml_threadpool_params_init(struct ggml_threadpool_params * p, int n_threads) {
p->n_threads = n_threads;
p->prio = 0; // default priority (usually means normal or inherited)
p->poll = 50; // hybrid-polling enabled
p->strict_cpu = false; // no strict placement (all threads share same cpumask)
p->paused = false; // threads are ready to go
memset(p->cpumask, 0, GGML_MAX_N_THREADS); // all-zero means use the default affinity (usually inherited)
}
struct ggml_threadpool_params ggml_threadpool_params_default(int n_threads) {
struct ggml_threadpool_params p;
ggml_threadpool_params_init(&p, n_threads);
return p;
}
bool ggml_threadpool_params_match(const struct ggml_threadpool_params * p0, const struct ggml_threadpool_params * p1) {
if (p0->n_threads != p1->n_threads ) return false;
if (p0->prio != p1->prio ) return false;
if (p0->poll != p1->poll ) return false;
if (p0->strict_cpu != p1->strict_cpu ) return false;
return memcmp(p0->cpumask, p1->cpumask, GGML_MAX_N_THREADS) == 0;
}
static struct ggml_threadpool * ggml_threadpool_new_impl(
struct ggml_threadpool_params * tpp,
struct ggml_cgraph * cgraph,