server : refactor multitask handling (#9274)

* server : remove multitask from server_task

* refactor completions handler

* fix embeddings

* use res_ok everywhere

* small change for handle_slots_action

* use unordered_set everywhere

* (try) fix test

* no more "mutable" lambda

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* use deque

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

examples/server/tests/features/parallel.feature

@@ -52,8 +52,8 @@ Feature: Parallel
     Then all prompts are predicted with <n_predict> tokens
     Examples:
       | streaming | n_predict |
-      | disabled  | 128       |
-      | enabled   | 64        |
+      | disabled  | 200       |
+      | enabled   | 200       |
 
   Scenario Outline: Multi users OAI completions compatibility no v1
     Given a system prompt You are a writer.

examples/server/tests/features/steps/steps.py

@@ -818,7 +818,7 @@ async def concurrent_requests(context, f_completion, *args, **kwargs):
     for prompt_no in range(context.n_prompts):
         shifted_args = [context.prompts.pop(), seeds[prompt_no], *args]
         context.concurrent_tasks.append(asyncio.create_task(f_completion(*shifted_args, **kwargs)))
-    await asyncio.sleep(0.1)
+    await asyncio.sleep(0.01)
 
 
 @step('the slot {slot_id:d} is saved with filename "{filename}"')

examples/server/tests/features/wrong_usages.feature

@@ -8,9 +8,12 @@ Feature: Wrong usage of llama.cpp server
   Scenario: Infinite loop
     Given a server listening on localhost:8080
     And   a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
+    And   42 as server seed
+    And   2048 KV cache size
     # Uncomment below to fix the issue
     #And   64 server max tokens to predict
     Then  the server is starting
+    Then  the server is healthy
     Given a prompt:
       """
       Go to: infinite loop

examples/server/utils.hpp

@@ -3,6 +3,14 @@
 #include "llama.h"
 #include "common.h"
 
+#ifndef NDEBUG
+// crash the server in debug mode, otherwise send an http 500 error
+#define CPPHTTPLIB_NO_EXCEPTIONS 1
+#endif
+// increase max payload length to allow use of larger context size
+#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
+#include "httplib.h"
+
 // Change JSON_ASSERT from assert() to GGML_ASSERT:
 #define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
@@ -279,6 +287,18 @@ static size_t find_partial_stop_string(const std::string &stop, const std::strin
     return std::string::npos;
 }
 
+static bool json_is_array_of_numbers(json data) {
+    if (data.is_array()) {
+        for (const auto & e : data) {
+            if (!e.is_number()) {
+                return false;
+            }
+        }
+        return true;
+    }
+    return false;
+}
+
 // TODO: reuse llama_detokenize
 template <class Iter>
 static std::string tokens_to_str(llama_context * ctx, Iter begin, Iter end) {
@@ -343,6 +363,19 @@ static json probs_vector_to_json(const llama_context * ctx, const std::vector<co
     return out;
 }
 
+static bool server_sent_event(httplib::DataSink & sink, const char * event, json & data) {
+    const std::string str =
+        std::string(event) + ": " +
+        data.dump(-1, ' ', false, json::error_handler_t::replace) +
+        "\n\n";
+
+    LOG_VERBOSE("data stream", {
+        { "to_send", str }
+    });
+
+    return sink.write(str.c_str(), str.size());
+}
+
 //
 // OAI utils
 //