server: support /models/sse on single-model mode (#32398)

* server: support /models/sse on single-model mode

* nits

* nits
This commit is contained in:
Xuan-Son Nguyen authored and GitHub committed 2026-11-22 17:52:56 +01:00
1 parent 8d60873dfb
commit 0b51bb2fed
12 files changed
+273 -113

No files matched your search

+123 -63
View File
@@ -109,6 +109,7 @@ static server_role_type server_role_detect(const common_params & params, server_
}
// a server given no model is a router
const bool has_model = !params.model.path.empty()
|| !params.model.url.empty()
|| !params.model.hf_repo.empty()
|| !params.model.docker_repo.empty();
return has_model ? SERVER_ROLE_INSTANCE : SERVER_ROLE_ROUTER;
@@ -363,66 +364,45 @@ static bool server_on_listening(server_http_context & ctx_http, const common_par
return true;
}
//
// download worker: a child of the router that pulls a model into the cache and reports the progress
//
struct server_download_state : public common_download_callback {
server_role * role;
// throttled download progress, shared by the download worker and single-model mode
struct server_download_progress : public common_download_callback {
// called under the lock, the files are downloaded in parallel threads
std::function<void(const common_download_progress &)> on_progress;
std::function<bool()> should_stop;
// files download in parallel threads: throttle each file on its own, a shared
// timer lets a small, fast file (e.g. a draft) starve the updates of the others
std::mutex progress_mutex;
// throttle each file on its own, a shared timer lets a small, fast file (e.g. a draft) starve the updates of the others
std::mutex mutex;
std::unordered_map<std::string, int64_t> last_progress_time;
bool is_ok = false;
server_download_state(server_role * r) : role(r) {}
bool run(common_params & params) {
try {
common_models_handler handler = common_models_handler_init(params, LLAMA_EXAMPLE_SERVER);
common_models_handler_apply(handler, params, this);
is_ok = true;
} catch (const std::exception & e) {
auto model_name = params.model.get_name();
SRV_ERR("download failed for model name=%s: %s\n", model_name.c_str(), e.what());
is_ok = false;
}
return is_ok;
}
void on_progress(const common_download_progress & p) {
json data = {
{"url", p.url},
{"downloaded", p.downloaded},
{"total", p.total},
};
role->notify_to_router(server_state_to_str(SERVER_STATE_DOWNLOADING), data);
void notify(const common_download_progress & p) {
std::lock_guard<std::mutex> lk(mutex);
on_progress(p);
}
void on_start(const common_download_progress & p) override {
on_progress(p);
notify(p);
}
void on_update(const common_download_progress & p) override {
int64_t now = ggml_time_ms();
// throttle progress updates to avoid flooding logs; the first update of a file
// always passes, it carries the file's total size
{
std::lock_guard<std::mutex> lk(progress_mutex);
auto it = last_progress_time.find(p.url);
if (it != last_progress_time.end() && now - it->second < 100) {
return;
}
last_progress_time[p.url] = now;
// the first update of a file always passes, it carries the file's total size
std::lock_guard<std::mutex> lk(mutex);
auto it = last_progress_time.find(p.url);
if (it != last_progress_time.end() && now - it->second < 100) {
return;
}
last_progress_time[p.url] = now;
on_progress(p);
}
void on_done(const common_download_progress & p, bool) override {
on_progress(p);
notify(p);
}
bool is_cancelled() const override {
return should_stop ? should_stop() : false;
}
};
//
// download worker: a child of the router that pulls a model into the cache and reports the progress
//
static int server_run_download(common_params & params, server_role & role) {
auto cancelled = std::make_shared<std::atomic<bool>>(false);
@@ -431,12 +411,27 @@ static int server_run_download(common_params & params, server_role & role) {
cancelled->store(true, std::memory_order_relaxed);
});
server_download_state dl(&role);
server_download_progress dl;
dl.on_progress = [&role](const common_download_progress & p) {
role.notify_to_router(server_state_to_str(SERVER_STATE_DOWNLOADING), {
{"url", p.url},
{"downloaded", p.downloaded},
{"total", p.total},
});
};
dl.should_stop = [cancelled]() {
return cancelled->load(std::memory_order_relaxed);
};
bool ok = dl.run(params);
bool ok = true;
try {
common_models_handler handler = common_models_handler_init(params, LLAMA_EXAMPLE_SERVER);
common_models_handler_apply(handler, params, &dl);
} catch (const std::exception & e) {
auto model_name = params.model.get_name();
SRV_ERR("download failed for model name=%s: %s\n", model_name.c_str(), e.what());
ok = false;
}
role.notify_to_router(server_state_to_str(SERVER_STATE_DOWNLOADING), {
{"result", ok ? "download_finished" : "download_failed"},
@@ -638,15 +633,21 @@ static int server_run_router(common_params & params, int argc, char ** argv, con
//
static int server_run_instance(common_params & params, server_role & role, common_models_handler & models_handler, const server_run_opts & opts) {
// -hf / docker: download if needed and resolve the local path. a child resolves what the router downloaded
if (opts.resolve_model) {
try {
common_models_handler_apply(models_handler, params);
} catch (const std::exception & e) {
SRV_ERR("failed to download model: %s\n", e.what());
return 1;
// a router child reports its state to the router, a single-model server to its own /models/sse clients
const bool managed = role.is_managed_by_router();
const std::string model_name = server_get_model_name(params);
server_models_sse sse(/* replay_last */ true);
std::atomic<bool> sse_stopping = false;
auto notify = [&](const std::string & event, const json & data = nullptr) {
if (!managed) {
sse.notify(event, model_name, data);
}
}
};
auto notify_status = [&](server_model_status status, json data = json::object()) {
data["status"] = server_model_status_to_string(status);
notify("status_change", data);
};
// note: this is guaranteed to out-live ctx_http and tools
server_mcp mcp_mgr;
@@ -667,37 +668,82 @@ static int server_run_instance(common_params & params, server_role & role, commo
server_stream_make_get_handler(),
server_stream_make_lookup_handler(),
server_stream_make_delete_handler());
if (!managed) {
ctx_http.get("/models/sse", ex_wrapper(sse.make_handler([&sse_stopping]() {
return sse_stopping.load(std::memory_order_relaxed);
})));
}
if (!server_setup_features(ctx_http, params, mcp_mgr, tools, SERVER_ROLE_INSTANCE)) {
return 1;
}
// setup clean up function, to be called before exit
auto clean_up = [&ctx_http, &ctx_server, &mcp_mgr]() {
auto clean_up = [&ctx_http, &ctx_server, &mcp_mgr, &sse_stopping]() {
SRV_INF("%s: cleaning up before exit...\n", __func__);
// stop the session GC first, it finalizes live sessions and wakes pending readers
server_stream_session_manager_stop();
sse_stopping.store(true); // disconnect the SSE clients
ctx_http.stop();
ctx_server.terminate();
mcp_mgr.shutdown();
llama_backend_free();
};
// start the HTTP server before loading the model to be able to serve /health requests
// start the HTTP server before downloading and loading the model to be able to serve /health and /models/sse requests
if (!ctx_http.start()) {
clean_up();
SRV_ERR("%s", "exiting due to HTTP server error\n");
return 1;
}
// setup communication child --> router if necessary
if (role.is_managed_by_router()) {
ctx_server.set_state_callback([&](server_state state, json payload) {
role.notify_to_router(server_state_to_str(state), payload);
});
// -hf / docker: download if needed and resolve the local path. a child resolves what the router downloaded
if (opts.resolve_model) {
json progress = json::object(); // url -> {done, total}, the same shape as the router sends
server_download_progress dl;
dl.on_progress = [&](const common_download_progress & p) {
if (p.total == 0) {
return; // not started yet, or found in the cache
}
progress[p.url] = {
{"done", p.downloaded},
{"total", p.total},
};
notify("download_progress", {{"progress", progress}});
};
try {
common_models_handler_apply(models_handler, params, managed ? nullptr : &dl);
if (!progress.empty()) {
notify("download_finished");
}
} catch (const std::exception & e) {
SRV_ERR("failed to download model: %s\n", e.what());
notify("download_failed");
notify_status(SERVER_MODEL_STATUS_UNLOADED, {{"exit_code", 1}});
clean_up();
ctx_http.join();
return 1;
}
}
// setup communication child --> router, or to the SSE clients
ctx_server.set_state_callback([&](server_state state, json payload) {
if (managed) {
role.notify_to_router(server_state_to_str(state), payload);
return;
}
switch (state) {
case SERVER_STATE_LOADING: notify_status(SERVER_MODEL_STATUS_LOADING, {{"progress", payload}}); break;
case SERVER_STATE_READY: notify_status(SERVER_MODEL_STATUS_LOADED); break; // wakeup from sleeping
case SERVER_STATE_SLEEPING: notify_status(SERVER_MODEL_STATUS_SLEEPING); break;
default: break;
}
});
notify_status(SERVER_MODEL_STATUS_LOADING);
if (!ctx_server.load_model(params)) {
notify_status(SERVER_MODEL_STATUS_UNLOADED, {{"exit_code", 1}});
clean_up();
ctx_http.join();
SRV_ERR("%s", "exiting due to model loading error\n");
@@ -709,7 +755,22 @@ static int server_run_instance(common_params & params, server_role & role, commo
SRV_INF("%s", "model loaded\n");
json info = routes.get_model_info();
json memory;
if (const auto * ll_ctx = ctx_server.get_llama_context()) {
memory = server_model_memory(llama_n_ctx(ll_ctx), common_memory_breakdown_rows(ll_ctx)).to_json();
}
{
json data = {{"info", info}};
if (!memory.is_null()) {
data["memory"] = memory;
}
notify_status(SERVER_MODEL_STATUS_LOADED, data);
}
shutdown_handler = [&](int) {
sse_stopping.store(true);
mcp_mgr.shutdown();
// this will unblock start_loop()
ctx_server.terminate();
@@ -729,12 +790,11 @@ static int server_run_instance(common_params & params, server_role & role, commo
// optionally, notify router server that this instance is ready
std::thread monitor_thread;
if (role.is_managed_by_router()) {
if (managed) {
monitor_thread = role.setup(shutdown_handler);
json info = routes.get_model_info();
// the router tracks device memory from these reports
if (const auto * ll_ctx = ctx_server.get_llama_context()) {
info["memory"] = server_model_memory(llama_n_ctx(ll_ctx), common_memory_breakdown_rows(ll_ctx)).to_json();
if (!memory.is_null()) {
info["memory"] = memory;
}
role.notify_to_router(server_state_to_str(SERVER_STATE_READY), info);
}