[metrics] Add serveral observability metrics (#3868)

* Add several observability metrics

* [wenxin-tools-584] 【可观测性】支持查看本节点的并发数、剩余block_size、排队请求数等信息

* adjust some metrics and md files

* trigger ci

* adjust ci file

* trigger ci

* trigger ci

---------

Co-authored-by: K11OntheBoat <your_email@example.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

fastdeploy/cache_manager/cache_metrics.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 """
 
+from fastdeploy.metrics.metrics import main_process_metrics
 from fastdeploy.utils import get_logger
 
 logger = get_logger("prefix_cache_manager", "prefix_cache_manager.log")
@@ -54,6 +55,11 @@ class CacheMetrics:
         self.cpu_hit_token_ratio = self.total_cpu_matched_token_num / self.total_token_num
         self.gpu_hit_token_ratio = self.total_gpu_matched_token_num / self.total_token_num
 
+        main_process_metrics.hit_req_rate.set(self.hit_req_ratio)
+        main_process_metrics.hit_token_rate.set(self.hit_token_ratio)
+        main_process_metrics.cpu_hit_token_rate.set(self.cpu_hit_token_ratio)
+        main_process_metrics.gpu_hit_token_rate.set(self.gpu_hit_token_ratio)
+
         logger.info(
             f"Metrics for all requests: req_count {self.req_count} hit_req_count {self.hit_req_count}"
             + f" hit_req_ratio {self.hit_req_ratio:.2f} hit_token_ratio {self.hit_token_ratio:.2f}"