]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1d2869c)
server : serve index.html with no-cache (#27006)
authorEmanuil Rusev <redacted>
Thu, 13 Aug 2026 14:59:45 +0000 (17:59 +0300)
committerGitHub <redacted>
Thu, 13 Aug 2026 14:59:45 +0000 (16:59 +0200)
commit981184e49a2710a7066ada728743a407d7b4c963
tree25596aa05ff4c8cd856ba156884719f198629b5etree
parent1d2869c6e54d5003f3927a79efbca0fefa034a6dcommit | diff
server : serve index.html with no-cache (#27006)

index.html was served with `max-age=31536000, immutable` like the hashed assets, but its name is stable while its contents change every build, so a cached copy pins the UI to an old build. It now revalidates via its existing ETag, which keeps the 304 for unchanged builds.
tools/server/server-http.cpp diff | blob | history
Packaging of ggml-org/llama.cpp