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/musa.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	ci/README.md
#	docs/build.md
#	docs/docker.md
#	ggml/CMakeLists.txt
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn-wmma-f16.cu
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tools/imatrix/README.md
#	tools/imatrix/imatrix.cpp
This commit is contained in:
Concedo 2025-07-25 19:53:13 +08:00
commit 0fcfbdb93c
33 changed files with 501 additions and 348 deletions
Download patch file Download diff file Expand all files Collapse all files

13
ggml/src/ggml-backend.cpp
View file

@ -647,6 +647,7 @@ struct ggml_backend_sched {
// pipeline parallelism support
int n_copies;
int cur_copy;
int next_copy;
ggml_backend_event_t events[GGML_SCHED_MAX_BACKENDS][GGML_SCHED_MAX_COPIES];
struct ggml_tensor * graph_inputs[GGML_SCHED_MAX_SPLIT_INPUTS];
int n_graph_inputs;
@ -1439,8 +1440,6 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s
}
}
sched->cur_copy = (sched->cur_copy + 1) % sched->n_copies;
return GGML_STATUS_SUCCESS;
}
@ -1541,10 +1540,10 @@ void ggml_backend_sched_reset(ggml_backend_sched_t sched) {
bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph * measure_graph) {
GGML_ASSERT((int)sched->hash_set.size >= measure_graph->n_nodes + measure_graph->n_leafs);
ggml_backend_sched_split_graph(sched, measure_graph);
ggml_backend_sched_synchronize(sched);
ggml_backend_sched_split_graph(sched, measure_graph);
if (!ggml_gallocr_reserve_n(sched->galloc, &sched->graph, sched->node_backend_ids, sched->leaf_backend_ids)) {
return false;
}
@ -1556,6 +1555,10 @@ bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph *
bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph) {
GGML_ASSERT((int)sched->hash_set.size >= graph->n_nodes + graph->n_leafs);
GGML_ASSERT(!sched->is_alloc);
sched->cur_copy = sched->next_copy;
sched->next_copy = (sched->next_copy + 1) % sched->n_copies;
ggml_backend_sched_split_graph(sched, graph);
@ -1596,7 +1599,7 @@ void ggml_backend_sched_synchronize(ggml_backend_sched_t sched) {
// if the graph is not already allocated, always use copy 0 after a synchronization
// this ensures that during generation the same copy is used every time,
// which avoids changes in the graph that could cause CUDA or other graphs to be disabled
sched->cur_copy = 0;
sched->next_copy = 0;
}
}