]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
kv-cache : rework kv_cell (#13706)
authorGeorgi Gerganov <redacted>
Sun, 25 May 2025 13:34:36 +0000 (16:34 +0300)
committerGitHub <redacted>
Sun, 25 May 2025 13:34:36 +0000 (16:34 +0300)
commitde2ef53a4b2c0d703749a309d19fe68fd8f1b9ac
tree5c075a1a9863eab3d0546e04d9d8957e8d1346f1
parentc508256db2de2b032e19c8ed833f4683c827c9a1
kv-cache : rework kv_cell (#13706)

* 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
include/llama.h
src/llama-context.cpp
src/llama-cparams.cpp
src/llama-cparams.h
src/llama-kv-cache.cpp
src/llama-kv-cache.h
src/llama-kv-cells.h [new file with mode: 0644]
src/llama-memory.h