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

rpc : early register backend devices (#11262)

Browse source 
Early register RPC devices and do not propagate RPC specifics in the
llama model structures.

ref: #10609
This commit is contained in:
Radoslav Gerganov 2025-01-17 10:57:09 +02:00 • committed by GitHub
parent a133566d34
commit 667d72846c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 61 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

27
common/arg.cpp
View file

@ -376,6 +376,30 @@ static std::vector<ggml_backend_dev_t> parse_device_list(const std::string & val
return devices;
}
static void add_rpc_devices(std::string servers) {
auto rpc_servers = string_split<std::string>(servers, ',');
if (rpc_servers.empty()) {
throw std::invalid_argument("no RPC servers specified");
}
ggml_backend_reg_t rpc_reg = ggml_backend_reg_by_name("RPC");
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");
}
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");
}
}
}
bool common_params_parse(int argc, char ** argv, common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
auto ctx_arg = common_params_parser_init(params, ex, print_usage);
const common_params params_org = ctx_arg.params; // the example can modify the default params
@ -1385,7 +1409,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--rpc"}, "SERVERS",
"comma separated list of RPC servers",
[](common_params & params, const std::string & value) {
params.rpc_servers = value;
add_rpc_devices(value);
GGML_UNUSED(params);
}
).set_env("LLAMA_ARG_RPC"));
}

1
common/common.cpp
View file

@ -1043,7 +1043,6 @@ struct llama_model_params common_model_params_to_llama(common_params & params) {
if (params.n_gpu_layers != -1) {
mparams.n_gpu_layers = params.n_gpu_layers;
}
mparams.rpc_servers = params.rpc_servers.c_str();
mparams.main_gpu = params.main_gpu;
mparams.split_mode = params.split_mode;
mparams.tensor_split = params.tensor_split;

1
common/common.h
View file

@ -246,7 +246,6 @@ struct common_params {
std::string lookup_cache_static = ""; // path of static ngram cache file for lookup decoding // NOLINT
std::string lookup_cache_dynamic = ""; // path of dynamic ngram cache file for lookup decoding // NOLINT
std::string logits_file = ""; // file for saving *all* logits // NOLINT
std::string rpc_servers = ""; // comma separated list of RPC servers // NOLINT
std::vector<std::string> in_files; // all input files
std::vector<std::string> antiprompt; // strings upon which more user input is prompted (a.k.a. reverse prompts)