vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/intel.Dockerfile
#	CMakeLists.txt
#	README.md
#	common/CMakeLists.txt
#	docs/multimodal.md
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	src/llama-context.cpp
This commit is contained in:
Concedo 2025-06-14 09:05:45 +08:00
commit 5f9e96e82d
18 changed files with 505 additions and 247 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama-kv-cache-recurrent.cpp
View file

@ -359,10 +359,10 @@ llama_pos llama_kv_cache_recurrent::seq_pos_max(llama_seq_id seq_id) const {
return result;
}
llama_memory_state_ptr llama_kv_cache_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled, bool logits_all) {
llama_memory_state_ptr llama_kv_cache_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled) {
GGML_UNUSED(embd_pooled);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false, logits_all);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false);
std::vector<llama_ubatch> ubatches;