llama : move end-user examples to tools directory (#13249)
* llama : move end-user examples to tools directory --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Diego Devesa
GitHub
parent
b34443923c
commit
1d36b3670b
213 changed files with 226 additions and 190 deletions
4
tools/rpc/CMakeLists.txt
Normal file
4
tools/rpc/CMakeLists.txt
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
set(TARGET rpc-server)
|
||||
add_executable(${TARGET} rpc-server.cpp)
|
||||
target_link_libraries(${TARGET} PRIVATE ggml)
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_17)
|
||||
85
tools/rpc/README.md
Normal file
85
tools/rpc/README.md
Normal file
|
|
@ -0,0 +1,85 @@
|
|||
## 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:
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
rpcb<-->|TCP|srva
|
||||
rpcb<-->|TCP|srvb
|
||||
rpcb<-.->|TCP|srvn
|
||||
subgraph hostn[Host N]
|
||||
srvn[rpc-server]<-.->backend3["Backend (CUDA,Metal,etc.)"]
|
||||
end
|
||||
subgraph hostb[Host B]
|
||||
srvb[rpc-server]<-->backend2["Backend (CUDA,Metal,etc.)"]
|
||||
end
|
||||
subgraph hosta[Host A]
|
||||
srva[rpc-server]<-->backend["Backend (CUDA,Metal,etc.)"]
|
||||
end
|
||||
subgraph host[Main Host]
|
||||
local["Backend (CUDA,Metal,etc.)"]<-->ggml[llama-cli]
|
||||
ggml[llama-cli]<-->rpcb[RPC backend]
|
||||
end
|
||||
style hostn stroke:#66,stroke-width:2px,stroke-dasharray: 5 5
|
||||
```
|
||||
|
||||
Each host can run a different backend, e.g. one with CUDA and another with Metal.
|
||||
You can also run multiple `rpc-server` instances on the same host, each with a different backend.
|
||||
|
||||
## Usage
|
||||
|
||||
On each host, build the corresponding backend with `cmake` and add `-DGGML_RPC=ON` to the build options.
|
||||
For example, to build the CUDA backend with RPC support:
|
||||
|
||||
```bash
|
||||
mkdir build-rpc-cuda
|
||||
cd build-rpc-cuda
|
||||
cmake .. -DGGML_CUDA=ON -DGGML_RPC=ON
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
Then, start the `rpc-server` with the backend:
|
||||
|
||||
```bash
|
||||
$ bin/rpc-server -p 50052
|
||||
create_backend: using CUDA backend
|
||||
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
|
||||
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
|
||||
ggml_cuda_init: found 1 CUDA devices:
|
||||
Device 0: NVIDIA T1200 Laptop GPU, compute capability 7.5, VMM: yes
|
||||
Starting RPC server on 0.0.0.0:50052
|
||||
```
|
||||
|
||||
When using the CUDA backend, you can specify the device with the `CUDA_VISIBLE_DEVICES` environment variable, e.g.:
|
||||
```bash
|
||||
$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052
|
||||
```
|
||||
This way you can run multiple `rpc-server` instances on the same host, each with a different CUDA device.
|
||||
|
||||
|
||||
On the main host build `llama.cpp` for the local backend and add `-DGGML_RPC=ON` to the build options.
|
||||
Finally, when running `llama-cli`, use the `--rpc` option to specify the host and port of each `rpc-server`:
|
||||
|
||||
```bash
|
||||
$ bin/llama-cli -m ../models/tinyllama-1b/ggml-model-f16.gguf -p "Hello, my name is" --repeat-penalty 1.0 -n 64 --rpc 192.168.88.10:50052,192.168.88.11:50052 -ngl 99
|
||||
```
|
||||
|
||||
This way you can offload model layers to both local and remote devices.
|
||||
|
||||
### Local cache
|
||||
|
||||
The RPC server can use a local cache to store large tensors and avoid transferring them over the network.
|
||||
This can speed up model loading significantly, especially when using large models.
|
||||
To enable the cache, use the `-c` option:
|
||||
|
||||
```bash
|
||||
$ bin/rpc-server -c
|
||||
```
|
||||
|
||||
By default, the cache is stored in the `$HOME/.cache/llama.cpp/rpc` directory and can be controlled via the `LLAMA_CACHE` environment variable.
|
||||
326
tools/rpc/rpc-server.cpp
Normal file
326
tools/rpc/rpc-server.cpp
Normal file
|
|
@ -0,0 +1,326 @@
|
|||
#if defined(_MSC_VER)
|
||||
#define _SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING
|
||||
#endif
|
||||
|
||||
#include "ggml-cpu.h"
|
||||
|
||||
#ifdef GGML_USE_CUDA
|
||||
#include "ggml-cuda.h"
|
||||
#endif
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
#include "ggml-metal.h"
|
||||
#endif
|
||||
|
||||
#ifdef GGML_USE_VULKAN
|
||||
#include "ggml-vulkan.h"
|
||||
#endif
|
||||
|
||||
#ifdef GGML_USE_SYCL
|
||||
#include "ggml-sycl.h"
|
||||
#endif
|
||||
|
||||
#include "ggml-rpc.h"
|
||||
#ifdef _WIN32
|
||||
# define NOMINMAX
|
||||
# define DIRECTORY_SEPARATOR '\\'
|
||||
# include <locale>
|
||||
# include <windows.h>
|
||||
# include <fcntl.h>
|
||||
# include <io.h>
|
||||
#else
|
||||
# define DIRECTORY_SEPARATOR '/'
|
||||
# include <unistd.h>
|
||||
# include <sys/stat.h>
|
||||
#endif
|
||||
#include <codecvt>
|
||||
#include <string>
|
||||
#include <stdio.h>
|
||||
#include <vector>
|
||||
#include <filesystem>
|
||||
#include <algorithm>
|
||||
#include <thread>
|
||||
|
||||
namespace fs = std::filesystem;
|
||||
|
||||
// NOTE: this is copied from common.cpp to avoid linking with libcommon
|
||||
// returns true if successful, false otherwise
|
||||
static bool fs_create_directory_with_parents(const std::string & path) {
|
||||
#ifdef _WIN32
|
||||
std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;
|
||||
std::wstring wpath = converter.from_bytes(path);
|
||||
|
||||
// if the path already exists, check whether it's a directory
|
||||
const DWORD attributes = GetFileAttributesW(wpath.c_str());
|
||||
if ((attributes != INVALID_FILE_ATTRIBUTES) && (attributes & FILE_ATTRIBUTE_DIRECTORY)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
size_t pos_slash = 0;
|
||||
|
||||
// process path from front to back, procedurally creating directories
|
||||
while ((pos_slash = path.find('\\', pos_slash)) != std::string::npos) {
|
||||
const std::wstring subpath = wpath.substr(0, pos_slash);
|
||||
const wchar_t * test = subpath.c_str();
|
||||
|
||||
const bool success = CreateDirectoryW(test, NULL);
|
||||
if (!success) {
|
||||
const DWORD error = GetLastError();
|
||||
|
||||
// if the path already exists, ensure that it's a directory
|
||||
if (error == ERROR_ALREADY_EXISTS) {
|
||||
const DWORD attributes = GetFileAttributesW(subpath.c_str());
|
||||
if (attributes == INVALID_FILE_ATTRIBUTES || !(attributes & FILE_ATTRIBUTE_DIRECTORY)) {
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
pos_slash += 1;
|
||||
}
|
||||
|
||||
return true;
|
||||
#else
|
||||
// if the path already exists, check whether it's a directory
|
||||
struct stat info;
|
||||
if (stat(path.c_str(), &info) == 0) {
|
||||
return S_ISDIR(info.st_mode);
|
||||
}
|
||||
|
||||
size_t pos_slash = 1; // skip leading slashes for directory creation
|
||||
|
||||
// process path from front to back, procedurally creating directories
|
||||
while ((pos_slash = path.find('/', pos_slash)) != std::string::npos) {
|
||||
const std::string subpath = path.substr(0, pos_slash);
|
||||
struct stat info;
|
||||
|
||||
// if the path already exists, ensure that it's a directory
|
||||
if (stat(subpath.c_str(), &info) == 0) {
|
||||
if (!S_ISDIR(info.st_mode)) {
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
// create parent directories
|
||||
const int ret = mkdir(subpath.c_str(), 0755);
|
||||
if (ret != 0) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
pos_slash += 1;
|
||||
}
|
||||
|
||||
return true;
|
||||
#endif // _WIN32
|
||||
}
|
||||
|
||||
// NOTE: this is copied from common.cpp to avoid linking with libcommon
|
||||
static std::string fs_get_cache_directory() {
|
||||
std::string cache_directory = "";
|
||||
auto ensure_trailing_slash = [](std::string p) {
|
||||
// Make sure to add trailing slash
|
||||
if (p.back() != DIRECTORY_SEPARATOR) {
|
||||
p += DIRECTORY_SEPARATOR;
|
||||
}
|
||||
return p;
|
||||
};
|
||||
if (getenv("LLAMA_CACHE")) {
|
||||
cache_directory = std::getenv("LLAMA_CACHE");
|
||||
} else {
|
||||
#if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX)
|
||||
if (std::getenv("XDG_CACHE_HOME")) {
|
||||
cache_directory = std::getenv("XDG_CACHE_HOME");
|
||||
} else {
|
||||
cache_directory = std::getenv("HOME") + std::string("/.cache/");
|
||||
}
|
||||
#elif defined(__APPLE__)
|
||||
cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
|
||||
#elif defined(_WIN32)
|
||||
cache_directory = std::getenv("LOCALAPPDATA");
|
||||
#else
|
||||
# error Unknown architecture
|
||||
#endif
|
||||
cache_directory = ensure_trailing_slash(cache_directory);
|
||||
cache_directory += "llama.cpp";
|
||||
}
|
||||
return ensure_trailing_slash(cache_directory);
|
||||
}
|
||||
|
||||
struct rpc_server_params {
|
||||
std::string host = "127.0.0.1";
|
||||
int port = 50052;
|
||||
size_t backend_mem = 0;
|
||||
bool use_cache = false;
|
||||
int n_threads = std::max(1U, std::thread::hardware_concurrency()/2);
|
||||
};
|
||||
|
||||
static void print_usage(int /*argc*/, char ** argv, rpc_server_params params) {
|
||||
fprintf(stderr, "Usage: %s [options]\n\n", argv[0]);
|
||||
fprintf(stderr, "options:\n");
|
||||
fprintf(stderr, " -h, --help show this help message and exit\n");
|
||||
fprintf(stderr, " -t, --threads number of threads for the CPU backend (default: %d)\n", params.n_threads);
|
||||
fprintf(stderr, " -H HOST, --host HOST host to bind to (default: %s)\n", params.host.c_str());
|
||||
fprintf(stderr, " -p PORT, --port PORT port to bind to (default: %d)\n", params.port);
|
||||
fprintf(stderr, " -m MEM, --mem MEM backend memory size (in MB)\n");
|
||||
fprintf(stderr, " -c, --cache enable local file cache\n");
|
||||
fprintf(stderr, "\n");
|
||||
}
|
||||
|
||||
static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params & params) {
|
||||
std::string arg;
|
||||
for (int i = 1; i < argc; i++) {
|
||||
arg = argv[i];
|
||||
if (arg == "-H" || arg == "--host") {
|
||||
if (++i >= argc) {
|
||||
return false;
|
||||
}
|
||||
params.host = argv[i];
|
||||
} else if (arg == "-t" || arg == "--threads") {
|
||||
if (++i >= argc) {
|
||||
return false;
|
||||
}
|
||||
params.n_threads = std::stoi(argv[i]);
|
||||
if (params.n_threads <= 0) {
|
||||
fprintf(stderr, "error: invalid number of threads: %d\n", params.n_threads);
|
||||
return false;
|
||||
}
|
||||
} else if (arg == "-p" || arg == "--port") {
|
||||
if (++i >= argc) {
|
||||
return false;
|
||||
}
|
||||
params.port = std::stoi(argv[i]);
|
||||
if (params.port <= 0 || params.port > 65535) {
|
||||
return false;
|
||||
}
|
||||
} else if (arg == "-c" || arg == "--cache") {
|
||||
params.use_cache = true;
|
||||
} else if (arg == "-m" || arg == "--mem") {
|
||||
if (++i >= argc) {
|
||||
return false;
|
||||
}
|
||||
params.backend_mem = std::stoul(argv[i]) * 1024 * 1024;
|
||||
} else if (arg == "-h" || arg == "--help") {
|
||||
print_usage(argc, argv, params);
|
||||
exit(0);
|
||||
} else {
|
||||
fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
|
||||
print_usage(argc, argv, params);
|
||||
exit(0);
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
static ggml_backend_t create_backend(const rpc_server_params & params) {
|
||||
ggml_backend_t backend = NULL;
|
||||
#ifdef GGML_USE_CUDA
|
||||
fprintf(stderr, "%s: using CUDA backend\n", __func__);
|
||||
backend = ggml_backend_cuda_init(0); // init device 0
|
||||
if (!backend) {
|
||||
fprintf(stderr, "%s: ggml_backend_cuda_init() failed\n", __func__);
|
||||
}
|
||||
#elif GGML_USE_METAL
|
||||
fprintf(stderr, "%s: using Metal backend\n", __func__);
|
||||
backend = ggml_backend_metal_init();
|
||||
if (!backend) {
|
||||
fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__);
|
||||
}
|
||||
#elif GGML_USE_VULKAN
|
||||
fprintf(stderr, "%s: using Vulkan backend\n", __func__);
|
||||
backend = ggml_backend_vk_init(0); // init device 0
|
||||
if (!backend) {
|
||||
fprintf(stderr, "%s: ggml_backend_vulkan_init() failed\n", __func__);
|
||||
}
|
||||
#elif GGML_USE_SYCL
|
||||
fprintf(stderr, "%s: using SYCL backend\n", __func__);
|
||||
backend = ggml_backend_sycl_init(0); // init device 0
|
||||
if (!backend) {
|
||||
fprintf(stderr, "%s: ggml_backend_sycl_init() failed\n", __func__);
|
||||
}
|
||||
#endif
|
||||
|
||||
// if there aren't GPU Backends fallback to CPU backend
|
||||
if (!backend) {
|
||||
fprintf(stderr, "%s: using CPU backend\n", __func__);
|
||||
backend = ggml_backend_cpu_init();
|
||||
ggml_backend_cpu_set_n_threads(backend, params.n_threads);
|
||||
}
|
||||
return backend;
|
||||
}
|
||||
|
||||
static void get_backend_memory(size_t * free_mem, size_t * total_mem) {
|
||||
#ifdef GGML_USE_CUDA
|
||||
ggml_backend_cuda_get_device_memory(0, free_mem, total_mem);
|
||||
#elif GGML_USE_VULKAN
|
||||
ggml_backend_vk_get_device_memory(0, free_mem, total_mem);
|
||||
#elif GGML_USE_SYCL
|
||||
ggml_backend_sycl_get_device_memory(0, free_mem, total_mem);
|
||||
#else
|
||||
#ifdef _WIN32
|
||||
MEMORYSTATUSEX status;
|
||||
status.dwLength = sizeof(status);
|
||||
GlobalMemoryStatusEx(&status);
|
||||
*total_mem = status.ullTotalPhys;
|
||||
*free_mem = status.ullAvailPhys;
|
||||
#else
|
||||
long pages = sysconf(_SC_PHYS_PAGES);
|
||||
long page_size = sysconf(_SC_PAGE_SIZE);
|
||||
*total_mem = pages * page_size;
|
||||
*free_mem = *total_mem;
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
|
||||
int main(int argc, char * argv[]) {
|
||||
rpc_server_params params;
|
||||
if (!rpc_server_params_parse(argc, argv, params)) {
|
||||
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(params);
|
||||
if (!backend) {
|
||||
fprintf(stderr, "Failed to create backend\n");
|
||||
return 1;
|
||||
}
|
||||
std::string endpoint = params.host + ":" + std::to_string(params.port);
|
||||
size_t free_mem, total_mem;
|
||||
if (params.backend_mem > 0) {
|
||||
free_mem = params.backend_mem;
|
||||
total_mem = params.backend_mem;
|
||||
} else {
|
||||
get_backend_memory(&free_mem, &total_mem);
|
||||
}
|
||||
const char * cache_dir = nullptr;
|
||||
std::string cache_dir_str;
|
||||
if (params.use_cache) {
|
||||
cache_dir_str = fs_get_cache_directory() + "rpc/";
|
||||
if (!fs_create_directory_with_parents(cache_dir_str)) {
|
||||
fprintf(stderr, "Failed to create cache directory: %s\n", cache_dir_str.c_str());
|
||||
return 1;
|
||||
}
|
||||
cache_dir = cache_dir_str.c_str();
|
||||
}
|
||||
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.c_str());
|
||||
printf(" local cache : %s\n", cache_dir ? cache_dir : "n/a");
|
||||
printf(" backend memory : %zu MB\n", free_mem / (1024 * 1024));
|
||||
ggml_backend_rpc_start_server(backend, endpoint.c_str(), cache_dir, free_mem, total_mem);
|
||||
ggml_backend_free(backend);
|
||||
return 0;
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue