apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

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

Browse Source 
Co-authored-by: root <root@szzj-bcc-offline-1487319.szzj.baidu.com>
This commit is contained in:
Jiang-Jia-Jun
2026-02-09 10:27:56 +08:00
committed by GitHub
parent 15e01c6f61
commit 18e79dd660
4 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/cache_manager/prefix_cache_manager.py
+2
View File
@@ -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)