sync from b7516

This commit is contained in:
2026-01-16 11:16:14 +08:00
parent f4ae4cc7da
commit 6ee41dd9e3
380 changed files with 18435 additions and 38806 deletions

View File

@@ -19,7 +19,10 @@
#include <thread>
#include <vector>
#if defined(LLAMA_USE_HTTPLIB)
#if defined(LLAMA_USE_CURL)
#include <curl/curl.h>
#include <curl/easy.h>
#elif defined(LLAMA_USE_HTTPLIB)
#include "http.h"
#endif
@@ -154,21 +157,322 @@ static std::string read_etag(const std::string & path) {
return none;
}
static bool is_http_status_ok(int status) {
return status >= 200 && status < 400;
}
#ifdef LLAMA_USE_CURL
std::pair<std::string, std::string> common_download_split_repo_tag(const std::string & hf_repo_with_tag) {
auto parts = string_split<std::string>(hf_repo_with_tag, ':');
std::string tag = parts.size() > 1 ? parts.back() : "latest";
std::string hf_repo = parts[0];
if (string_split<std::string>(hf_repo, '/').size() != 2) {
throw std::invalid_argument("error: invalid HF repo format, expected <user>/<model>[:quant]\n");
//
// CURL utils
//
using curl_ptr = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
// cannot use unique_ptr for curl_slist, because we cannot update without destroying the old one
struct curl_slist_ptr {
struct curl_slist * ptr = nullptr;
~curl_slist_ptr() {
if (ptr) {
curl_slist_free_all(ptr);
}
}
return {hf_repo, tag};
};
static CURLcode common_curl_perf(CURL * curl) {
CURLcode res = curl_easy_perform(curl);
if (res != CURLE_OK) {
LOG_ERR("%s: curl_easy_perform() failed\n", __func__);
}
return res;
}
#if defined(LLAMA_USE_HTTPLIB)
// Send a HEAD request to retrieve the etag and last-modified headers
struct common_load_model_from_url_headers {
std::string etag;
std::string last_modified;
std::string accept_ranges;
};
struct FILE_deleter {
void operator()(FILE * f) const { fclose(f); }
};
static size_t common_header_callback(char * buffer, size_t, size_t n_items, void * userdata) {
common_load_model_from_url_headers * headers = (common_load_model_from_url_headers *) userdata;
static std::regex header_regex("([^:]+): (.*)\r\n");
static std::regex etag_regex("ETag", std::regex_constants::icase);
static std::regex last_modified_regex("Last-Modified", std::regex_constants::icase);
static std::regex accept_ranges_regex("Accept-Ranges", std::regex_constants::icase);
std::string header(buffer, n_items);
std::smatch match;
if (std::regex_match(header, match, header_regex)) {
const std::string & key = match[1];
const std::string & value = match[2];
if (std::regex_match(key, match, etag_regex)) {
headers->etag = value;
} else if (std::regex_match(key, match, last_modified_regex)) {
headers->last_modified = value;
} else if (std::regex_match(key, match, accept_ranges_regex)) {
headers->accept_ranges = value;
}
}
return n_items;
}
static size_t common_write_callback(void * data, size_t size, size_t nmemb, void * fd) {
return std::fwrite(data, size, nmemb, static_cast<FILE *>(fd));
}
// helper function to hide password in URL
static std::string llama_download_hide_password_in_url(const std::string & url) {
// Use regex to match and replace the user[:password]@ pattern in URLs
// Pattern: scheme://[user[:password]@]host[...]
static const std::regex url_regex(R"(^(?:[A-Za-z][A-Za-z0-9+.-]://)(?:[^/@]+@)?.$)");
std::smatch match;
if (std::regex_match(url, match, url_regex)) {
// match[1] = scheme (e.g., "https://")
// match[2] = user[:password]@ part
// match[3] = rest of URL (host and path)
return match[1].str() + "********@" + match[3].str();
}
return url; // No credentials found or malformed URL
}
static void common_curl_easy_setopt_head(CURL * curl, const std::string & url) {
// Set the URL, allow to follow http redirection
curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
# if defined(_WIN32)
// CURLSSLOPT_NATIVE_CA tells libcurl to use standard certificate store of
// operating system. Currently implemented under MS-Windows.
curl_easy_setopt(curl, CURLOPT_SSL_OPTIONS, CURLSSLOPT_NATIVE_CA);
# endif
curl_easy_setopt(curl, CURLOPT_NOBODY, 1L); // will trigger the HEAD verb
curl_easy_setopt(curl, CURLOPT_NOPROGRESS, 1L); // hide head request progress
curl_easy_setopt(curl, CURLOPT_HEADERFUNCTION, common_header_callback);
}
static void common_curl_easy_setopt_get(CURL * curl) {
curl_easy_setopt(curl, CURLOPT_NOBODY, 0L);
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, common_write_callback);
// display download progress
curl_easy_setopt(curl, CURLOPT_NOPROGRESS, 0L);
}
static bool common_pull_file(CURL * curl, const std::string & path_temporary) {
if (std::filesystem::exists(path_temporary)) {
const std::string partial_size = std::to_string(std::filesystem::file_size(path_temporary));
LOG_INF("%s: server supports range requests, resuming download from byte %s\n", __func__, partial_size.c_str());
const std::string range_str = partial_size + "-";
curl_easy_setopt(curl, CURLOPT_RANGE, range_str.c_str());
}
// Always open file in append mode could be resuming
std::unique_ptr<FILE, FILE_deleter> outfile(fopen(path_temporary.c_str(), "ab"));
if (!outfile) {
LOG_ERR("%s: error opening local file for writing: %s\n", __func__, path_temporary.c_str());
return false;
}
common_curl_easy_setopt_get(curl);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, outfile.get());
return common_curl_perf(curl) == CURLE_OK;
}
static bool common_download_head(CURL * curl,
curl_slist_ptr & http_headers,
const std::string & url,
const std::string & bearer_token) {
if (!curl) {
LOG_ERR("%s: error initializing libcurl\n", __func__);
return false;
}
http_headers.ptr = curl_slist_append(http_headers.ptr, "User-Agent: llama-cpp");
// Check if hf-token or bearer-token was specified
if (!bearer_token.empty()) {
std::string auth_header = "Authorization: Bearer " + bearer_token;
http_headers.ptr = curl_slist_append(http_headers.ptr, auth_header.c_str());
}
curl_easy_setopt(curl, CURLOPT_HTTPHEADER, http_headers.ptr);
common_curl_easy_setopt_head(curl, url);
return common_curl_perf(curl) == CURLE_OK;
}
// download one single file from remote URL to local path
static bool common_download_file_single_online(const std::string & url,
const std::string & path,
const std::string & bearer_token) {
static const int max_attempts = 3;
static const int retry_delay_seconds = 2;
for (int i = 0; i < max_attempts; ++i) {
std::string etag;
// Check if the file already exists locally
const auto file_exists = std::filesystem::exists(path);
if (file_exists) {
etag = read_etag(path);
} else {
LOG_INF("%s: no previous model file found %s\n", __func__, path.c_str());
}
bool head_request_ok = false;
bool should_download = !file_exists; // by default, we should download if the file does not exist
// Initialize libcurl
curl_ptr curl(curl_easy_init(), &curl_easy_cleanup);
common_load_model_from_url_headers headers;
curl_easy_setopt(curl.get(), CURLOPT_HEADERDATA, &headers);
curl_slist_ptr http_headers;
const bool was_perform_successful = common_download_head(curl.get(), http_headers, url, bearer_token);
if (!was_perform_successful) {
head_request_ok = false;
}
long http_code = 0;
curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &http_code);
if (http_code == 200) {
head_request_ok = true;
} else {
LOG_WRN("%s: HEAD invalid http status code received: %ld\n", __func__, http_code);
head_request_ok = false;
}
// if head_request_ok is false, we don't have the etag or last-modified headers
// we leave should_download as-is, which is true if the file does not exist
bool should_download_from_scratch = false;
if (head_request_ok) {
// check if ETag or Last-Modified headers are different
// if it is, we need to download the file again
if (!etag.empty() && etag != headers.etag) {
LOG_WRN("%s: ETag header is different (%s != %s): triggering a new download\n", __func__, etag.c_str(),
headers.etag.c_str());
should_download = true;
should_download_from_scratch = true;
}
}
const bool accept_ranges_supported = !headers.accept_ranges.empty() && headers.accept_ranges != "none";
if (should_download) {
if (file_exists &&
!accept_ranges_supported) { // Resumable downloads not supported, delete and start again.
LOG_WRN("%s: deleting previous downloaded file: %s\n", __func__, path.c_str());
if (remove(path.c_str()) != 0) {
LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
return false;
}
}
const std::string path_temporary = path + ".downloadInProgress";
if (should_download_from_scratch) {
if (std::filesystem::exists(path_temporary)) {
if (remove(path_temporary.c_str()) != 0) {
LOG_ERR("%s: unable to delete file: %s\n", __func__, path_temporary.c_str());
return false;
}
}
if (std::filesystem::exists(path)) {
if (remove(path.c_str()) != 0) {
LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
return false;
}
}
}
if (head_request_ok) {
write_etag(path, headers.etag);
}
// start the download
LOG_INF("%s: trying to download model from %s to %s (server_etag:%s, server_last_modified:%s)...\n",
__func__, llama_download_hide_password_in_url(url).c_str(), path_temporary.c_str(),
headers.etag.c_str(), headers.last_modified.c_str());
const bool was_pull_successful = common_pull_file(curl.get(), path_temporary);
if (!was_pull_successful) {
if (i + 1 < max_attempts) {
const int exponential_backoff_delay = std::pow(retry_delay_seconds, i) * 1000;
LOG_WRN("%s: retrying after %d milliseconds...\n", __func__, exponential_backoff_delay);
std::this_thread::sleep_for(std::chrono::milliseconds(exponential_backoff_delay));
} else {
LOG_ERR("%s: curl_easy_perform() failed after %d attempts\n", __func__, max_attempts);
}
continue;
}
long http_code = 0;
curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &http_code);
if (http_code < 200 || http_code >= 400) {
LOG_ERR("%s: invalid http status code received: %ld\n", __func__, http_code);
return false;
}
if (rename(path_temporary.c_str(), path.c_str()) != 0) {
LOG_ERR("%s: unable to rename file: %s to %s\n", __func__, path_temporary.c_str(), path.c_str());
return false;
}
} else {
LOG_INF("%s: using cached file: %s\n", __func__, path.c_str());
}
break;
}
return true;
}
std::pair<long, std::vector<char>> common_remote_get_content(const std::string & url, const common_remote_params & params) {
curl_ptr curl(curl_easy_init(), &curl_easy_cleanup);
curl_slist_ptr http_headers;
std::vector<char> res_buffer;
curl_easy_setopt(curl.get(), CURLOPT_URL, url.c_str());
curl_easy_setopt(curl.get(), CURLOPT_NOPROGRESS, 1L);
curl_easy_setopt(curl.get(), CURLOPT_FOLLOWLOCATION, 1L);
curl_easy_setopt(curl.get(), CURLOPT_VERBOSE, 0L);
typedef size_t(*CURLOPT_WRITEFUNCTION_PTR)(void * ptr, size_t size, size_t nmemb, void * data);
auto write_callback = [](void * ptr, size_t size, size_t nmemb, void * data) -> size_t {
auto data_vec = static_cast<std::vector<char> *>(data);
data_vec->insert(data_vec->end(), (char *)ptr, (char *)ptr + size * nmemb);
return size * nmemb;
};
curl_easy_setopt(curl.get(), CURLOPT_WRITEFUNCTION, static_cast<CURLOPT_WRITEFUNCTION_PTR>(write_callback));
curl_easy_setopt(curl.get(), CURLOPT_WRITEDATA, &res_buffer);
#if defined(_WIN32)
curl_easy_setopt(curl.get(), CURLOPT_SSL_OPTIONS, CURLSSLOPT_NATIVE_CA);
#endif
if (params.timeout > 0) {
curl_easy_setopt(curl.get(), CURLOPT_TIMEOUT, params.timeout);
}
if (params.max_size > 0) {
curl_easy_setopt(curl.get(), CURLOPT_MAXFILESIZE, params.max_size);
}
http_headers.ptr = curl_slist_append(http_headers.ptr, "User-Agent: llama-cpp");
for (const auto & header : params.headers) {
http_headers.ptr = curl_slist_append(http_headers.ptr, header.c_str());
}
curl_easy_setopt(curl.get(), CURLOPT_HTTPHEADER, http_headers.ptr);
CURLcode res = curl_easy_perform(curl.get());
if (res != CURLE_OK) {
std::string error_msg = curl_easy_strerror(res);
throw std::runtime_error("error: cannot make GET request: " + error_msg);
}
long res_code;
curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &res_code);
return { res_code, std::move(res_buffer) };
}
#elif defined(LLAMA_USE_HTTPLIB)
class ProgressBar {
static inline std::mutex mutex;
@@ -313,11 +617,9 @@ static bool common_pull_file(httplib::Client & cli,
}
// download one single file from remote URL to local path
// returns status code or -1 on error
static int common_download_file_single_online(const std::string & url,
static bool common_download_file_single_online(const std::string & url,
const std::string & path,
const std::string & bearer_token,
const common_header_list & custom_headers) {
const std::string & bearer_token) {
static const int max_attempts = 3;
static const int retry_delay_seconds = 2;
@@ -327,9 +629,6 @@ static int common_download_file_single_online(const std::string & url,
if (!bearer_token.empty()) {
default_headers.insert({"Authorization", "Bearer " + bearer_token});
}
for (const auto & h : custom_headers) {
default_headers.emplace(h.first, h.second);
}
cli.set_default_headers(default_headers);
const bool file_exists = std::filesystem::exists(path);
@@ -348,10 +647,8 @@ static int common_download_file_single_online(const std::string & url,
LOG_WRN("%s: HEAD invalid http status code received: %d\n", __func__, head ? head->status : -1);
if (file_exists) {
LOG_INF("%s: Using cached file (HEAD failed): %s\n", __func__, path.c_str());
return 304; // 304 Not Modified - fake cached response
return true;
}
return head->status; // cannot use cached file, return raw status code
// TODO: maybe retry only on certain codes
}
std::string etag;
@@ -383,12 +680,12 @@ static int common_download_file_single_online(const std::string & url,
if (file_exists) {
if (!should_download_from_scratch) {
LOG_INF("%s: using cached file: %s\n", __func__, path.c_str());
return 304; // 304 Not Modified - fake cached response
return true;
}
LOG_WRN("%s: deleting previous downloaded file: %s\n", __func__, path.c_str());
if (remove(path.c_str()) != 0) {
LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
return -1;
return false;
}
}
@@ -400,7 +697,7 @@ static int common_download_file_single_online(const std::string & url,
existing_size = std::filesystem::file_size(path_temporary);
} else if (remove(path_temporary.c_str()) != 0) {
LOG_ERR("%s: unable to delete file: %s\n", __func__, path_temporary.c_str());
return -1;
return false;
}
}
@@ -421,16 +718,15 @@ static int common_download_file_single_online(const std::string & url,
if (std::rename(path_temporary.c_str(), path.c_str()) != 0) {
LOG_ERR("%s: unable to rename file: %s to %s\n", __func__, path_temporary.c_str(), path.c_str());
return -1;
return false;
}
if (!etag.empty()) {
write_etag(path, etag);
}
return head->status; // TODO: use actual GET status?
break;
}
return -1; // max attempts reached
return true;
}
std::pair<long, std::vector<char>> common_remote_get_content(const std::string & url,
@@ -438,9 +734,13 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
auto [cli, parts] = common_http_client(url);
httplib::Headers headers = {{"User-Agent", "llama-cpp"}};
for (const auto & header : params.headers) {
headers.emplace(header.first, header.second);
size_t pos = header.find(':');
if (pos != std::string::npos) {
headers.emplace(header.substr(0, pos), header.substr(pos + 1));
} else {
headers.emplace(header, "");
}
}
if (params.timeout > 0) {
@@ -465,45 +765,36 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
return { res->status, std::move(buf) };
}
int common_download_file_single(const std::string & url,
const std::string & path,
const std::string & bearer_token,
bool offline,
const common_header_list & headers) {
#endif // LLAMA_USE_CURL
#if defined(LLAMA_USE_CURL) || defined(LLAMA_USE_HTTPLIB)
static bool common_download_file_single(const std::string & url,
const std::string & path,
const std::string & bearer_token,
bool offline) {
if (!offline) {
return common_download_file_single_online(url, path, bearer_token, headers);
return common_download_file_single_online(url, path, bearer_token);
}
if (!std::filesystem::exists(path)) {
LOG_ERR("%s: required file is not available in cache (offline mode): %s\n", __func__, path.c_str());
return -1;
return false;
}
LOG_INF("%s: using cached file (offline mode): %s\n", __func__, path.c_str());
return 304; // Not Modified - fake cached response
return true;
}
// download multiple files from remote URLs to local paths
// the input is a vector of pairs <url, path>
static bool common_download_file_multiple(const std::vector<std::pair<std::string, std::string>> & urls,
const std::string & bearer_token,
bool offline,
const common_header_list & headers) {
static bool common_download_file_multiple(const std::vector<std::pair<std::string, std::string>> & urls, const std::string & bearer_token, bool offline) {
// Prepare download in parallel
std::vector<std::future<bool>> futures_download;
futures_download.reserve(urls.size());
for (auto const & item : urls) {
futures_download.push_back(
std::async(
std::launch::async,
[&bearer_token, offline, &headers](const std::pair<std::string, std::string> & it) -> bool {
const int http_status = common_download_file_single(it.first, it.second, bearer_token, offline, headers);
return is_http_status_ok(http_status);
},
item
)
);
futures_download.push_back(std::async(std::launch::async, [bearer_token, offline](const std::pair<std::string, std::string> & it) -> bool {
return common_download_file_single(it.first, it.second, bearer_token, offline);
}, item));
}
// Wait for all downloads to complete
@@ -516,18 +807,17 @@ static bool common_download_file_multiple(const std::vector<std::pair<std::strin
return true;
}
bool common_download_model(const common_params_model & model,
const std::string & bearer_token,
bool offline,
const common_header_list & headers) {
bool common_download_model(
const common_params_model & model,
const std::string & bearer_token,
bool offline) {
// Basic validation of the model.url
if (model.url.empty()) {
LOG_ERR("%s: invalid model url\n", __func__);
return false;
}
const int http_status = common_download_file_single(model.url, model.path, bearer_token, offline, headers);
if (!is_http_status_ok(http_status)) {
if (!common_download_file_single(model.url, model.path, bearer_token, offline)) {
return false;
}
@@ -586,26 +876,27 @@ bool common_download_model(const common_params_model & model,
}
// Download in parallel
common_download_file_multiple(urls, bearer_token, offline, headers);
common_download_file_multiple(urls, bearer_token, offline);
}
return true;
}
common_hf_file_res common_get_hf_file(const std::string & hf_repo_with_tag,
const std::string & bearer_token,
bool offline,
const common_header_list & custom_headers) {
// the returned hf_repo is without tag
auto [hf_repo, tag] = common_download_split_repo_tag(hf_repo_with_tag);
common_hf_file_res common_get_hf_file(const std::string & hf_repo_with_tag, const std::string & bearer_token, bool offline) {
auto parts = string_split<std::string>(hf_repo_with_tag, ':');
std::string tag = parts.size() > 1 ? parts.back() : "latest";
std::string hf_repo = parts[0];
if (string_split<std::string>(hf_repo, '/').size() != 2) {
throw std::invalid_argument("error: invalid HF repo format, expected <user>/<model>[:quant]\n");
}
std::string url = get_model_endpoint() + "v2/" + hf_repo + "/manifests/" + tag;
// headers
common_header_list headers = custom_headers;
headers.push_back({"Accept", "application/json"});
std::vector<std::string> headers;
headers.push_back("Accept: application/json");
if (!bearer_token.empty()) {
headers.push_back({"Authorization", "Bearer " + bearer_token});
headers.push_back("Authorization: Bearer " + bearer_token);
}
// Important: the User-Agent must be "llama-cpp" to get the "ggufFile" field in the response
// User-Agent header is already set in common_remote_get_content, no need to set it here
@@ -661,7 +952,7 @@ common_hf_file_res common_get_hf_file(const std::string & hf_repo_with_tag,
} else if (res_code == 401) {
throw std::runtime_error("error: model is private or does not exist; if you are accessing a gated model, please provide a valid HF token");
} else {
throw std::runtime_error(string_format("error from HF API (%s), response code: %ld, data: %s", url.c_str(), res_code, res_str.c_str()));
throw std::runtime_error(string_format("error from HF API, response code: %ld, data: %s", res_code, res_str.c_str()));
}
// check response
@@ -740,10 +1031,9 @@ std::string common_docker_resolve_model(const std::string & docker) {
const std::string url_prefix = "https://registry-1.docker.io/v2/" + repo;
std::string manifest_url = url_prefix + "/manifests/" + tag;
common_remote_params manifest_params;
manifest_params.headers.push_back({"Authorization", "Bearer " + token});
manifest_params.headers.push_back({"Accept",
"application/vnd.docker.distribution.manifest.v2+json,application/vnd.oci.image.manifest.v1+json"
});
manifest_params.headers.push_back("Authorization: Bearer " + token);
manifest_params.headers.push_back(
"Accept: application/vnd.docker.distribution.manifest.v2+json,application/vnd.oci.image.manifest.v1+json");
auto manifest_res = common_remote_get_content(manifest_url, manifest_params);
if (manifest_res.first != 200) {
throw std::runtime_error("Failed to get Docker manifest, HTTP code: " + std::to_string(manifest_res.first));
@@ -780,8 +1070,7 @@ std::string common_docker_resolve_model(const std::string & docker) {
std::string local_path = fs_get_cache_file(model_filename);
const std::string blob_url = url_prefix + "/blobs/" + gguf_digest;
const int http_status = common_download_file_single(blob_url, local_path, token, false, {});
if (!is_http_status_ok(http_status)) {
if (!common_download_file_single(blob_url, local_path, token, false)) {
throw std::runtime_error("Failed to download Docker Model");
}
@@ -795,11 +1084,11 @@ std::string common_docker_resolve_model(const std::string & docker) {
#else
common_hf_file_res common_get_hf_file(const std::string &, const std::string &, bool, const common_header_list &) {
common_hf_file_res common_get_hf_file(const std::string &, const std::string &, bool) {
throw std::runtime_error("download functionality is not enabled in this build");
}
bool common_download_model(const common_params_model &, const std::string &, bool, const common_header_list &) {
bool common_download_model(const common_params_model &, const std::string &, bool) {
throw std::runtime_error("download functionality is not enabled in this build");
}
@@ -807,15 +1096,7 @@ std::string common_docker_resolve_model(const std::string &) {
throw std::runtime_error("download functionality is not enabled in this build");
}
int common_download_file_single(const std::string &,
const std::string &,
const std::string &,
bool,
const common_header_list &) {
throw std::runtime_error("download functionality is not enabled in this build");
}
#endif // defined(LLAMA_USE_HTTPLIB)
#endif // LLAMA_USE_CURL || LLAMA_USE_HTTPLIB
std::vector<common_cached_model_info> common_list_cached_models() {
std::vector<common_cached_model_info> models;