docs: fix metrics endpoint description in server README (#22879)

* docs: fix metrics endpoint description in server README

Required model query parameter for router mode described.

Removed metrics:
- llamacpp:kv_cache_usage_ratio
- llamacpp:kv_cache_tokens

Added metrics:
- llamacpp:prompt_seconds_total
- llamacpp:tokens_predicted_seconds_total
- llamacpp:n_decode_total
- llamacpp:n_busy_slots_per_decode

* server: fix metrics type for n_busy_slots_per_decode metric

tools/server/server-context.cpp

@@ -3622,10 +3622,6 @@ void server_routes::init_routes() {
                     {"name",  "n_tokens_max"},
                     {"help",  "Largest observed n_tokens."},
                     {"value",  res_task->n_tokens_max}
-            }, {
-                    {"name",  "n_busy_slots_per_decode"},
-                    {"help",  "Average number of busy slots per llama_decode() call"},
-                    {"value",  (float) res_task->n_busy_slots_total / std::max((float) res_task->n_decode_total, 1.f)}
             }}},
             {"gauge", {{
                     {"name",  "prompt_tokens_seconds"},
@@ -3643,6 +3639,10 @@ void server_routes::init_routes() {
                     {"name",  "requests_deferred"},
                     {"help",  "Number of requests deferred."},
                     {"value",  (uint64_t) res_task->n_tasks_deferred}
+            },{
+                    {"name",  "n_busy_slots_per_decode"},
+                    {"help",  "Average number of busy slots per llama_decode() call"},
+                    {"value",  (float) res_task->n_busy_slots_total / std::max((float) res_task->n_decode_total, 1.f)}
             }}}
         };