]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 83a88bd)
llama : refactor kv cache guard (#12695)
authorGeorgi Gerganov <redacted>
Wed, 2 Apr 2025 11:32:59 +0000 (14:32 +0300)
committerGitHub <redacted>
Wed, 2 Apr 2025 11:32:59 +0000 (14:32 +0300)
commita10b36c91a091f4606710fba4e9327fd71e0e738
tree50ddfe899b9d4702926a50c6af121c682e9a842btree
parent83a88bd6affbe148a622ac730952ac5b8b585979commit | diff
llama : refactor kv cache guard (#12695)

* llama : refactor kv cache guard

ggml-ci

* cont : fix comment [no ci]

* llama : fix kv_cache restore logic

ggml-ci

* context : simplify kv cache updates

ggml-ci

* cont : better name [no ci]

* llama : fix llama_decode return code when could not find KV slot

ggml-ci

* context : change log err -> warn [no ci]

* kv-cache : add comment + warning
examples/parallel/parallel.cpp diff | blob | history
src/llama-context.cpp diff | blob | history
src/llama-kv-cache.cpp diff | blob | history
src/llama-kv-cache.h diff | blob | history
Packaging of ggml-org/llama.cpp