]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 36c5913)
server : add arg for disabling prompt caching (#18776)
authorRadoslav Gerganov <redacted>
Mon, 12 Jan 2026 17:21:34 +0000 (19:21 +0200)
committerGitHub <redacted>
Mon, 12 Jan 2026 17:21:34 +0000 (19:21 +0200)
commitbcf7546160982f56bc290d2e538544bbc0772f63
tree26b6f64dec8c66a73e43f051e93080aa0f20437ftree
parent36c5913c45264b1a38bccd7900d7670590650d55commit | diff
server : add arg for disabling prompt caching (#18776)

* server : add arg for disabling prompt caching

Disabling prompt caching is useful for clients who are restricted to
sending only OpenAI-compat requests and want deterministic
responses.

* address review comments

* address review comments
common/arg.cpp diff | blob | history
common/common.h diff | blob | history
tools/server/server-task.cpp diff | blob | history
Packaging of ggml-org/llama.cpp