]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 389c7d4)
rpc : fix misleading error log (#21184)
authorRadoslav Gerganov <redacted>
Mon, 30 Mar 2026 14:05:11 +0000 (17:05 +0300)
committerGitHub <redacted>
Mon, 30 Mar 2026 14:05:11 +0000 (17:05 +0300)
commitcad2d3884c75e3b2e4736654295d1f1a5c29aa48
treeca74784b129237e5009f7058baeac93cb5c7e750tree
parent389c7d4955ba55c7418afaebf7c23d9ed64ef707commit | diff
rpc : fix misleading error log (#21184)

When RPC is running with a remote backend which doesn't have init_tensor
function (like CPU and Metal), the server log gets full with error
messages saying that init_tensor is being called with null buffer which
is incorrect. This patch fixes this.
ggml/src/ggml-rpc/ggml-rpc.cpp diff | blob | history
Packaging of ggml-org/llama.cpp