Jiaxin Shan
Jiaxin Shan
@dittops I think the problem is vLLM community update the CI after this PR is out, result in some failures on the CI checking. I try to close this PR...
@dittops now it's working. thanks! no need to cut new PRs
/gemini review
the change overall looks good to me. I will address gemini's feedback in later refactor
 I can confirm that infinistore server is up before benchmarking, I also sent a warm up request before batch requests
 the client didn't see result returned but seems the cache server is still working at this moment ---- Update: it's because I use `debug` level logs and it is...
client logs 
server side logs 
