tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : clarify deprecation message (#13794)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-05-26 12:57:50 +03:00
committed by GitHub
parent 9012eb9b45
commit 22229314fc
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/llama.h
View File

@ -612,11 +612,11 @@ extern "C" {
// Returns the number of tokens in the KV cache (slow, use only for debug) // 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 // If a KV cell has multiple sequences assigned to it, it will be counted multiple times
DEPRECATED(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"); "Use llama_kv_self_seq_pos_max() and llama_kv_self_seq_pos_min() instead (https://github.com/ggml-org/llama.cpp/issues/13793)");
// Returns the number of used KV cells (i.e. have at least one sequence assigned to them) // Returns the number of used KV cells (i.e. have at least one sequence assigned to them)
DEPRECATED(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"); "Use llama_kv_self_seq_pos_max() and llama_kv_self_seq_pos_min() instead (https://github.com/ggml-org/llama.cpp/issues/13793)");
// Clear the KV cache - both cell info is erased and KV data is zeroed // Clear the KV cache - both cell info is erased and KV data is zeroed
LLAMA_API void llama_kv_self_clear( LLAMA_API void llama_kv_self_clear(