]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c4f89d8)
llama : do not allocate KV cache for "vocab_only == true" (#682)
authorStephan Walter <redacted>
Sun, 2 Apr 2023 07:18:53 +0000 (07:18 +0000)
committerGitHub <redacted>
Sun, 2 Apr 2023 07:18:53 +0000 (10:18 +0300)
commit81040f10aae3160317c5787c9c59acb219927826
tree6cd8c03882662779c13d7be51e5576b5133a4f7ctree
parentc4f89d8d73aab4318a6c61e3835135adfcf55407commit | diff
llama : do not allocate KV cache for "vocab_only == true" (#682)

Fixes sanitizer CI
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp