]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a16cce8)
server : honor --embd-normalize CLI arg (#23125)
authorRares Vernica <redacted>
Sun, 17 May 2026 06:39:04 +0000 (23:39 -0700)
committerGitHub <redacted>
Sun, 17 May 2026 06:39:04 +0000 (09:39 +0300)
commit1a68ec93781c9014ac0a1e174887ae703c6deaf8
treefefefd6bd53234a7e4d8939e8000d67e021def26tree
parenta16cce81d3996f9872114e94a177831c6285d1f6commit | diff
server : honor --embd-normalize CLI arg (#23125)

The --embd-normalize flag was registered only for the embedding and debug
examples, so llama-server rejected it and the /embedding handler used a
hard-coded default of 2 (L2). Add LLAMA_EXAMPLE_SERVER to the flag's
example set and read params.embd_normalize as the handler's default. The
per-request "embd_normalize" body field continues to override.
common/arg.cpp diff | blob | history
tools/server/server-context.cpp diff | blob | history
Packaging of ggml-org/llama.cpp