Closed FuryMartin closed 2 months ago
[APPROVALNOTIFIER] This PR is NOT APPROVED
This pull-request has been approved by:
To complete the pull request process, please assign jaypume after the PR has been reviewed.
You can assign the PR to them by writing /assign @jaypume
in a comment when ready.
The full list of commands accepted by this bot can be found here.
This PR should be reviewed by @hsj576.
The overall work is good, basically completed the pretest requirements.
Thanks!
Considering that this PR is just a demonstration, should I close it?
What type of PR is this?
/kind design
What this PR does / why we need it:
This is a demo for #130. I have implemented a cloud-edge collaborative strategy named query-routing.
The whole principle for query-routing is as below, which will route user's query to cloud or edge model based on its difficulty coefficiency:
For task 1, I used a modified Sedna package to support jsonl data evaluation. For task 2, I implemented query-routing based on Ianvs. For task 3, I left the results in README.md. The design details can be found in cloud-edge-collaboration-inference-for-llm
Which issue(s) this PR fixes:
Fixes #130