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:
#	common/CMakeLists.txt
#	common/arg.cpp
#	common/chat.cpp
#	examples/parallel/README.md
#	examples/parallel/parallel.cpp
#	ggml/cmake/common.cmake
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	models/ggml-vocab-bert-bge.gguf.inp
#	models/ggml-vocab-bert-bge.gguf.out
#	models/ggml-vocab-command-r.gguf.inp
#	models/ggml-vocab-command-r.gguf.out
#	models/ggml-vocab-deepseek-coder.gguf.inp
#	models/ggml-vocab-deepseek-coder.gguf.out
#	models/ggml-vocab-deepseek-llm.gguf.inp
#	models/ggml-vocab-deepseek-llm.gguf.out
#	models/ggml-vocab-falcon.gguf.inp
#	models/ggml-vocab-falcon.gguf.out
#	models/ggml-vocab-gpt-2.gguf.inp
#	models/ggml-vocab-gpt-2.gguf.out
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	models/ggml-vocab-llama-spm.gguf.inp
#	models/ggml-vocab-llama-spm.gguf.out
#	models/ggml-vocab-mpt.gguf.inp
#	models/ggml-vocab-mpt.gguf.out
#	models/ggml-vocab-phi-3.gguf.inp
#	models/ggml-vocab-phi-3.gguf.out
#	models/ggml-vocab-qwen2.gguf.inp
#	models/ggml-vocab-qwen2.gguf.out
#	models/ggml-vocab-refact.gguf.inp
#	models/ggml-vocab-refact.gguf.out
#	models/ggml-vocab-starcoder.gguf.inp
#	models/ggml-vocab-starcoder.gguf.out
#	requirements/requirements-gguf_editor_gui.txt
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/run/run.cpp
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo 2025-05-31 13:04:21 +08:00
commit b08dca65ed
62 changed files with 3208 additions and 27493 deletions
Download patch file Download diff file Expand all files Collapse all files

15
ggml/src/ggml-backend.cpp
View file

@ -1346,7 +1346,10 @@ static bool ggml_backend_sched_alloc_splits(ggml_backend_sched_t sched) {
// allocate graph
if (backend_ids_changed || !ggml_gallocr_alloc_graph(sched->galloc, &sched->graph)) {
// the re-allocation may cause the split inputs to be moved to a different address
ggml_backend_sched_synchronize(sched);
// synchronize without ggml_backend_sched_synchronize to avoid changing cur_copy
for (int i = 0; i < sched->n_backends; i++) {
ggml_backend_synchronize(sched->backends[i]);
}
#ifndef NDEBUG
GGML_LOG_DEBUG("%s: failed to allocate graph, reserving (backend_ids_changed = %d)\n", __func__, backend_ids_changed);
#endif
@ -1570,7 +1573,6 @@ bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgra
ggml_backend_sched_split_graph(sched, graph);
if (!ggml_backend_sched_alloc_splits(sched)) {
return false;
}
@ -1604,9 +1606,12 @@ void ggml_backend_sched_synchronize(ggml_backend_sched_t sched) {
for (int i = 0; i < sched->n_backends; i++) {
ggml_backend_synchronize(sched->backends[i]);
}
// reset the current copy to 0 so that the graphs will be similar during generation
// necessary for CUDA graphs
sched->cur_copy = 0;
if (!sched->is_alloc) {
// 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;
}
}
void ggml_backend_sched_set_eval_callback(ggml_backend_sched_t sched, ggml_backend_sched_eval_callback callback, void * user_data) {