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/workflows/build.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	README.md
#	docs/build.md
#	docs/install.md
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
This commit is contained in:
Concedo 2025-06-05 11:03:34 +08:00
commit bc89b465a8
35 changed files with 1070 additions and 288 deletions
Download patch file Download diff file Expand all files Collapse all files

19
src/llama-kv-cache-recurrent.cpp
View file

@ -1,6 +1,7 @@
#include "llama-kv-cache-recurrent.h"
#include "llama-impl.h"
#include "llama-io.h"
#include "llama-batch.h"
#include "llama-model.h"
@ -386,6 +387,13 @@ llama_memory_state_ptr llama_kv_cache_recurrent::init_full() {
return std::make_unique<llama_kv_cache_recurrent_state>(LLAMA_MEMORY_STATUS_SUCCESS, this);
}
llama_memory_state_ptr llama_kv_cache_recurrent::init_update(llama_context * lctx, bool optimize) {
GGML_UNUSED(lctx);
GGML_UNUSED(optimize);
return std::make_unique<llama_kv_cache_recurrent_state>(LLAMA_MEMORY_STATUS_NO_UPDATE);
}
bool llama_kv_cache_recurrent::prepare(const std::vector<llama_ubatch> & ubatches) {
// simply remember the full state because it is very small for this type of cache
// TODO: optimize
@ -419,17 +427,6 @@ bool llama_kv_cache_recurrent::prepare(const std::vector<llama_ubatch> & ubatche
return success;
}
bool llama_kv_cache_recurrent::update(llama_context & lctx) {
GGML_UNUSED(lctx);
// noop
return false;
}
void llama_kv_cache_recurrent::defrag_sched(float thold) {
GGML_UNUSED(thold);
// noop
}
bool llama_kv_cache_recurrent::find_slot(const llama_ubatch & ubatch) {
const uint32_t n_tokens = ubatch.n_tokens;
const uint32_t n_seqs = ubatch.n_seqs;