vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 02:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge commit 'ab86335760' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/release.yml
#	examples/retrieval/retrieval.cpp
#	examples/simple-chat/simple-chat.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	requirements/requirements-convert_hf_to_gguf.txt
#	requirements/requirements-convert_hf_to_gguf_update.txt
#	requirements/requirements-convert_lora_to_gguf.txt
#	tools/run/run.cpp
This commit is contained in:
Concedo 2025-05-23 11:41:36 +08:00
commit 22ef97d7d3
23 changed files with 495 additions and 231 deletions
Download patch file Download diff file Expand all files Collapse all files

6
include/llama.h
View file

@ -612,10 +612,12 @@ extern "C" {
// Returns the number of tokens in the KV cache (slow, use only for debug)
// If a KV cell has multiple sequences assigned to it, it will be counted multiple times
LLAMA_API int32_t llama_kv_self_n_tokens(const struct llama_context * ctx);
DEPRECATED(LLAMA_API int32_t llama_kv_self_n_tokens(const struct llama_context * ctx),
"Use llama_kv_self_seq_pos_max() instead");
// Returns the number of used KV cells (i.e. have at least one sequence assigned to them)
LLAMA_API int32_t llama_kv_self_used_cells(const struct llama_context * ctx);
DEPRECATED(LLAMA_API int32_t llama_kv_self_used_cells(const struct llama_context * ctx),
"Use llama_kv_self_seq_pos_max() instead");
// Clear the KV cache - both cell info is erased and KV data is zeroed
LLAMA_API void llama_kv_self_clear(