CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

rpc : use backend registry, support dl backends (#13304)

Browse Source
This commit is contained in:
Diego Devesa
2025-05-04 21:25:43 +02:00
committed by GitHub
parent 6eb7d25c70
commit 9fdfcdaedd
4 changed files with 116 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml-rpc/ggml-rpc.cpp
View File

@@ -1594,6 +1594,14 @@ static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
const char * cache_dir,
size_t free_mem, size_t total_mem) {
printf("Starting RPC server v%d.%d.%d\n",
RPC_PROTO_MAJOR_VERSION,
RPC_PROTO_MINOR_VERSION,
RPC_PROTO_PATCH_VERSION);
printf(" endpoint : %s\n", endpoint);
printf(" local cache : %s\n", cache_dir ? cache_dir : "n/a");
printf(" backend memory : %zu MB\n", free_mem / (1024 * 1024));
std::string host;
int port;
if (!parse_endpoint(endpoint, host, port)) {
@@ -1753,6 +1761,9 @@ static void * ggml_backend_rpc_get_proc_address(ggml_backend_reg_t reg, const ch
if (std::strcmp(name, "ggml_backend_rpc_add_device") == 0) {
return (void *)ggml_backend_rpc_add_device;
}
if (std::strcmp(name, "ggml_backend_rpc_start_server") == 0) {
return (void *)ggml_backend_rpc_start_server;
}
return NULL;
GGML_UNUSED(reg);