upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

cli : move to HTTP-based implementation (#24948)

Browse Source 
* cli: move to HTTP-based implementation

* wip

* working

* remote server ok

* cli support router mode

Co-authored-by: Piotr Wilkin <ilintar@gmail.com>

* case: router with only one model

* Apply suggestions from code review

Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>

* remove outdated comment

* use destructor instead

* add ftype

* cli-view --> cli-ui

* pimpl

* no more json in header

* nits fixes

* also show model aliases

---------

Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
This commit is contained in:
Xuan-Son Nguyen
2026-07-08 14:52:43 +02:00
committed by GitHub
parent 07e012afdc
commit c264f65ff9
14 changed files with 1336 additions and 724 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
tools/server/server-models.cpp
View File

@@ -7,6 +7,7 @@
#include "build-info.h"
#include "preset.h"
#include "download.h"
#include "http.h"
#include <cpp-httplib/httplib.h> // TODO: remove this once we use HTTP client from download.h
#include <optional>
@@ -28,14 +29,7 @@
#include <sstream>
#include <cstring>
#ifdef _WIN32
#include <winsock2.h>
#include <windows.h>
#else
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>
#ifndef _WIN32
extern char **environ;
#endif
@@ -716,66 +710,6 @@ std::optional<server_model_meta> server_models::get_meta(const std::string & nam
return std::nullopt;
}
static int get_free_port() {
#ifdef _WIN32
WSADATA wsaData;
if (WSAStartup(MAKEWORD(2, 2), &wsaData) != 0) {
return -1;
}
typedef SOCKET native_socket_t;
#define INVALID_SOCKET_VAL INVALID_SOCKET
#define CLOSE_SOCKET(s) closesocket(s)
#else
typedef int native_socket_t;
#define INVALID_SOCKET_VAL -1
#define CLOSE_SOCKET(s) close(s)
#endif
native_socket_t sock = socket(AF_INET, SOCK_STREAM, 0);
if (sock == INVALID_SOCKET_VAL) {
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
struct sockaddr_in serv_addr;
std::memset(&serv_addr, 0, sizeof(serv_addr));
serv_addr.sin_family = AF_INET;
serv_addr.sin_addr.s_addr = htonl(INADDR_ANY);
serv_addr.sin_port = htons(0);
if (bind(sock, (struct sockaddr*)&serv_addr, sizeof(serv_addr)) != 0) {
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
#ifdef _WIN32
int namelen = sizeof(serv_addr);
#else
socklen_t namelen = sizeof(serv_addr);
#endif
if (getsockname(sock, (struct sockaddr*)&serv_addr, &namelen) != 0) {
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
int port = ntohs(serv_addr.sin_port);
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return port;
}
// helper to convert vector<string> to char **
// pointers are only valid as long as the original vector is valid
static std::vector<char *> to_char_ptr_array(const std::vector<std::string> & vec) {
@@ -879,7 +813,7 @@ void server_models::load(const std::string & name, const load_options & opts) {
// prepare new instance info
instance_t inst;
inst.meta = meta;
inst.meta.port = get_free_port();
inst.meta.port = common_http_get_free_port();
inst.meta.status = SERVER_MODEL_STATUS_LOADING;
inst.meta.loaded_info = json{};
inst.meta.last_used = ggml_time_ms();