vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge commit from fork

Browse source
This commit is contained in:
Georgi Gerganov 2024-08-09 23:03:21 +03:00 • committed by GitHub
parent 6afd1a99dc
commit b72942fac9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 53 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/rpc/README.md
View file

@ -1,5 +1,9 @@
## Overview
> [!IMPORTANT]
> This example and the RPC backend are currently in a proof-of-concept development stage. As such, the functionality is fragile and
> insecure. **Never run the RPC server on an open network or in a sensitive environment!**
The `rpc-server` allows running `ggml` backend on a remote host.
The RPC backend communicates with one or several instances of `rpc-server` and offloads computations to them.
This can be used for distributed LLM inference with `llama.cpp` in the following way:

13
examples/rpc/rpc-server.cpp
View file

@ -16,7 +16,7 @@
#include <stdio.h>
struct rpc_server_params {
std::string host = "0.0.0.0";
std::string host = "127.0.0.1";
int port = 50052;
size_t backend_mem = 0;
};
@ -114,6 +114,17 @@ int main(int argc, char * argv[]) {
fprintf(stderr, "Invalid parameters\n");
return 1;
}
if (params.host != "127.0.0.1") {
fprintf(stderr, "\n");
fprintf(stderr, "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n");
fprintf(stderr, "WARNING: Host ('%s') is != '127.0.0.1'\n", params.host.c_str());
fprintf(stderr, " Never expose the RPC server to an open network!\n");
fprintf(stderr, " This is an experimental feature and is not secure!\n");
fprintf(stderr, "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n");
fprintf(stderr, "\n");
}
ggml_backend_t backend = create_backend();
if (!backend) {
fprintf(stderr, "Failed to create backend\n");