triton-lang/triton

[Question] Is it possible to cache the autotune output and re-use it later on ?

開放

#1,072 建立於 2023年1月18日

 (7 則留言) (2 個反應) (0 位負責人)MLIR (3,136 個分叉)github user discovery
help wanted

倉庫指標

星標
 (19,995 顆星)
PR 合併指標
 (平均合併 2天 18小時) (30 天內合併 185 個 PR)

描述

Dear OpenAI Triton Team,

Here is my use case. I am deploying models and the more requests they get, the faster they become. After a large number of requests, it seems the auto-tune converges.

I wonder if that state can be cached and re-used when restarting the server ?

Best, T.C

貢獻者指南