Skip to content

Conversation

liyonghua0910
Copy link
Collaborator

@liyonghua0910 liyonghua0910 commented Aug 5, 2025

为 YIYANAdapter 新增的若干指标,第 4 列为最终添加的指标名,其中有两个指标是复用当前 FD 的指标,其余均为新增指标:

image

Copy link

paddle-bot bot commented Aug 5, 2025

Thanks for your contribution!

@paddle-bot paddle-bot bot added the contributor External developers label Aug 5, 2025
@property
def num_free_blocks(self):
return len(self.gpu_free_block_list) + len(self.cpu_free_block_list)

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这几个我们可以直接复用 resource_manager 里面的接口

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cache_manager 是 resource_manager 的属性,我想在 cache_manager 里分配/回收 GPU 块时记录块的变化,所以不太方便引用 resource_manager,现在删掉这两个 property 了,直接用 len(self.gpu_free_block_list) 更新剩余 GPU 块。

@liyonghua0910 liyonghua0910 merged commit d18a637 into PaddlePaddle:feature/online/unify_code_20250804 Aug 21, 2025
1 check passed
liyonghua0910 added a commit to liyonghua0910/FastDeploy that referenced this pull request Aug 26, 2025
* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code
liyonghua0910 added a commit to liyonghua0910/FastDeploy that referenced this pull request Aug 26, 2025
* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code
Jiang-Jia-Jun pushed a commit that referenced this pull request Aug 28, 2025
* [feat] add metrics for yiyan adapter (#3219)

* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code

* [fix] fix error
Jiang-Jia-Jun pushed a commit that referenced this pull request Aug 30, 2025
* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code
co63oc pushed a commit to co63oc/FastDeploy that referenced this pull request Aug 31, 2025
…e#3614)

* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
contributor External developers
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants