]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : fix session saving/loading (#3400)
authorGeorgi Gerganov <redacted>
Tue, 3 Oct 2023 18:04:01 +0000 (21:04 +0300)
committerGitHub <redacted>
Tue, 3 Oct 2023 18:04:01 +0000 (21:04 +0300)
commitac2219fef34eb5b713c286c34c6e4162c39c8f3b
tree00d1bdad46d4995188ff084ae6178b9ff55f7431
parent48be797ffbd80b062f55778e09e97180eb25d2ab
llama : fix session saving/loading (#3400)

* llama : fix session saving/loading

* llama : temp fix for clearing "future" tokens from the KV cache

* llama : fix handling of "future" tokens when loading sessions

* llama : fix comments for llama_kv_cache API
examples/chat-persistent.sh
examples/main/main.cpp
examples/parallel/parallel.cpp
examples/server/server.cpp
examples/speculative/speculative.cpp
llama.cpp
llama.h