]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: db16e28)
llama-bench : use local GPUs along with RPC servers (#14917)
authorRadoslav Gerganov <redacted>
Mon, 28 Jul 2025 15:59:04 +0000 (18:59 +0300)
committerGitHub <redacted>
Mon, 28 Jul 2025 15:59:04 +0000 (18:59 +0300)
commitc556418b600ad5792440942079d93e393595688b
treea9788107752318ab8f55d4b5fc4164256efb7b28tree
parentdb16e2831c0f344f041af3d067db81c42b16eb22commit | diff
llama-bench : use local GPUs along with RPC servers (#14917)

Currently if RPC servers are specified with '--rpc' and there is a local
GPU available (e.g. CUDA), the benchmark will be performed only on the
RPC device(s) but the backend result column will say "CUDA,RPC" which is
incorrect. This patch is adding all local GPU devices and makes
llama-bench consistent with llama-cli.
tools/llama-bench/llama-bench.cpp diff | blob | history
Packaging of ggml-org/llama.cpp