mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-25 09:38:35 -04:00
main : add self-extend support (#4815)
* examples : add passkey test * passkey : better prints * passkey : select pass key pos from CLI * passkey : simplify n_past logic * llama : "self-extend"-like context extension * passkey : add comment * main : add Self-Extend support * llama : add comment about llama_kv_cache_seq_div
This commit is contained in:
4
llama.h
4
llama.h
@@ -484,6 +484,10 @@ extern "C" {
|
||||
llama_pos p1,
|
||||
llama_pos delta);
|
||||
|
||||
// Integer division of the positions by factor of `d > 1`
|
||||
// If the KV cache is RoPEd, the KV data is updated accordingly
|
||||
// p0 < 0 : [0, p1]
|
||||
// p1 < 0 : [p0, inf)
|
||||
LLAMA_API void llama_kv_cache_seq_div(
|
||||
struct llama_context * ctx,
|
||||
llama_seq_id seq_id,
|
||||
|
Reference in New Issue
Block a user