]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a5735e4)
llama : offload to RPC in addition to other backends (#7640)
authorRadoslav Gerganov <redacted>
Mon, 3 Jun 2024 17:03:26 +0000 (20:03 +0300)
committerGitHub <redacted>
Mon, 3 Jun 2024 17:03:26 +0000 (20:03 +0300)
commitbde7cd3cd949c1a85d3a199498ac98e78039d46f
tree738364c20669cea19d3ca5df2baec036429b9b40tree
parenta5735e4426b19a3ebd0c653ad8ac01420458ee95commit | diff
llama : offload to RPC in addition to other backends (#7640)

* llama : offload to RPC in addition to other backends

* - fix copy_tensor being called on the src buffer instead of the dst buffer

- always initialize views in the view_src buffer

- add RPC backend to Makefile build

- add endpoint to all RPC object names

* add rpc-server to Makefile

* Update llama.cpp

Co-authored-by: slaren <redacted>
---------

Co-authored-by: slaren <redacted>
Makefile diff | blob | history
ggml-alloc.c diff | blob | history
ggml-backend.c diff | blob | history
ggml-backend.h diff | blob | history
ggml-rpc.cpp diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp