[Metrics] Support cpu-cache-block-num (#6390)

Co-authored-by: root <root@szzj-bcc-offline-1487319.szzj.baidu.com>

docs/online_serving/metrics.md

@@ -37,6 +37,7 @@ After FastDeploy is launched, it supports continuous monitoring of the FastDeplo
 | KV Cache | `fastdeploy:available_gpu_block_num` | Gauge | Available GPU blocks in cache (including unreleased prefix blocks) | count |
 | KV Cache | `fastdeploy:free_gpu_block_num` | Gauge | Number of free GPU blocks in cache | count |
 | KV Cache | `fastdeploy:max_gpu_block_num` | Gauge | Total number of GPU blocks initialized at startup | count |
+| KV Cache | `fastdeploy:max_cpu_block_num` | Gauge | Total number of CPU blocks initialized at startup | count |
 | KV Cache | `fastdeploy:available_gpu_resource` | Gauge | Ratio of available GPU blocks to total GPU blocks | % |
 | KV Cache | `fastdeploy:gpu_cache_usage_perc` | Gauge | GPU KV cache utilization | % |
 | KV Cache | `fastdeploy:send_cache_failed_num` | Counter | Total number of cache send failures | count |

docs/zh/online_serving/metrics.md

@@ -36,7 +36,8 @@
 | KV缓存 | `fastdeploy:prefix_cpu_cache_token_num`   | Counter   | 位于 CPU 上的前缀缓存 token 总数  | 个   |
 | KV缓存 | `fastdeploy:available_gpu_block_num`      | Gauge     | 缓存中可用的 GPU 块数量（包含尚未正式释放的前缀缓存块）| 个   |
 | KV缓存 | `fastdeploy:free_gpu_block_num`           | Gauge     | 缓存中的可用块数             | 个   |
-| KV缓存 | `fastdeploy:max_gpu_block_num`            | Gauge     | 服务启动时确定的总块数        | 个   |
+| KV缓存 | `fastdeploy:max_gpu_block_num`            | Gauge     | 服务启动时确定的 GPU 总块数        | 个   |
+| KV缓存 | `fastdeploy:max_cpu_block_num`            | Gauge     | 服务启动时确定的 CPU 总块数        | 个   |
 | KV缓存 | `fastdeploy:available_gpu_resource`       | Gauge     | 可用块占比，即可用 GPU 块数量 / 最大GPU块数量| 百分比   |
 | KV缓存 | `fastdeploy:gpu_cache_usage_perc`         | Gauge     | GPU 上的 KV 缓存使用率          | 百分比    |
 | KV缓存 | `fastdeploy:send_cache_failed_num`        | Counter   | 发送缓存失败的总次数          | 个   |

fastdeploy/cache_manager/prefix_cache_manager.py

@@ -129,6 +129,7 @@ class PrefixCacheManager:
         )
 
         main_process_metrics.max_gpu_block_num.set(self.num_gpu_blocks)
+        main_process_metrics.max_cpu_block_num.set(self.num_cpu_blocks)
         main_process_metrics.available_gpu_block_num.set(self.num_gpu_blocks)
         main_process_metrics.free_gpu_block_num.set(self.num_gpu_blocks)
         main_process_metrics.available_gpu_resource.set(1.0)
@@ -457,6 +458,7 @@ class PrefixCacheManager:
         self.node_id_pool = list(range(self.num_gpu_blocks + self.num_cpu_blocks))
 
         main_process_metrics.max_gpu_block_num.set(self.num_gpu_blocks)
+        main_process_metrics.max_cpu_block_num.set(self.num_cpu_blocks)
         main_process_metrics.available_gpu_block_num.set(self.num_gpu_blocks)
         main_process_metrics.free_gpu_block_num.set(self.num_gpu_blocks)
         main_process_metrics.available_gpu_resource.set(1.0)

fastdeploy/metrics/metrics.py

@@ -158,6 +158,7 @@ class MetricsManager:
     available_gpu_block_num: "Gauge"
     free_gpu_block_num: "Gauge"
     max_gpu_block_num: "Gauge"
+    max_cpu_block_num: "Gauge"
     available_gpu_resource: "Gauge"
     requests_number: "Counter"
     send_cache_failed_num: "Counter"
@@ -235,7 +236,13 @@ class MetricsManager:
         "max_gpu_block_num": {
             "type": Gauge,
             "name": "fastdeploy:max_gpu_block_num",
-            "description": "Number of total blocks determined when service started",
+            "description": "Number of total GPU blocks determined when service started",
+            "kwargs": {},
+        },
+        "max_cpu_block_num": {
+            "type": Gauge,
+            "name": "fastdeploy:max_cpu_block_num",
+            "description": "Number of total CPU blocks determined when service started",
             "kwargs": {},
         },
         "available_gpu_resource": {