CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

rpc : add support for multiple devices (#16276)

Browse Source 
* rpc : add support for multiple devices

Allow rpc-server to expose multiple devices from a single endpoint.
Change RPC protocol to include device identifier where needed.

closes: #15210

* fixes

* use ggml_backend_reg_t

* address review comments

* fix llama-bench backend report

* address review comments, change device naming

* fix cmd order
This commit is contained in:
Radoslav Gerganov
2025-10-04 12:49:16 +03:00
committed by GitHub
parent e29acf74fe
commit 898acba681
7 changed files with 403 additions and 245 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
common/arg.cpp
View File

@@ -1615,18 +1615,14 @@ static void add_rpc_devices(const std::string & servers) {
if (!rpc_reg) {
throw std::invalid_argument("failed to find RPC backend");
}
typedef ggml_backend_dev_t (*ggml_backend_rpc_add_device_t)(const char * endpoint);
ggml_backend_rpc_add_device_t ggml_backend_rpc_add_device_fn = (ggml_backend_rpc_add_device_t) ggml_backend_reg_get_proc_address(rpc_reg, "ggml_backend_rpc_add_device");
if (!ggml_backend_rpc_add_device_fn) {
throw std::invalid_argument("failed to find RPC device add function");
typedef ggml_backend_reg_t (*ggml_backend_rpc_add_server_t)(const char * endpoint);
ggml_backend_rpc_add_server_t ggml_backend_rpc_add_server_fn = (ggml_backend_rpc_add_server_t) ggml_backend_reg_get_proc_address(rpc_reg, "ggml_backend_rpc_add_server");
if (!ggml_backend_rpc_add_server_fn) {
throw std::invalid_argument("failed to find RPC add server function");
}
for (const auto & server : rpc_servers) {
ggml_backend_dev_t dev = ggml_backend_rpc_add_device_fn(server.c_str());
if (dev) {
ggml_backend_device_register(dev);
} else {
throw std::invalid_argument("failed to register RPC device");
}
auto reg = ggml_backend_rpc_add_server_fn(server.c_str());
ggml_backend_register(reg);
}
}