ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

kv-cache : rework kv_cell (#13706)

Browse source 
* kv-cache : rework kv_cell

ggml-ci

* kv-cells : use "shift" instead of "delta" consistently

ggml-ci

* llama : add llama_max_parallel_sequences()

ggml-ci

* kv-cells : update comments [no ci]

* context : fail upon construction if sequences exceed max value

ggml-ci

* kv-cells : get_pos() -> pos_get() + comments

ggml-ci

* kv-cells : fix tracking of "used" cells

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-05-25 16:34:36 +03:00 • committed by GitHub
parent c508256db2
commit de2ef53a4b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 470 additions and 253 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-memory.h
View file

@ -22,7 +22,7 @@ public:
virtual bool seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) = 0;
virtual void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) = 0;
virtual void seq_keep(llama_seq_id seq_id) = 0;
virtual void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos delta) = 0;
virtual void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos shift) = 0;
virtual void seq_div (llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) = 0;
virtual llama_pos seq_pos_min(llama_seq_id seq_id) const = 0;