-
-
Notifications
You must be signed in to change notification settings - Fork 5.6k
Revert #57979 (and following #58083 #58082) #58182
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@nanosoldier |
Your benchmark job has completed - possible performance regressions were detected. A full report can be found here. |
Your benchmark job has completed - no performance regressions were detected. A full report can be found here. |
Looks like this is confirmed to fix the issues introduced by those PRs |
/cc @serenity4 @Keno Also this seems to require Cthulhu to be updated accordingly. |
Personally, I think the impact on the overall inference pipeline is limited, because these commits don't slow down the |
Yes, can we please actually investigate things? These were not perf optimizations but API cleanups for downstream consumers (which are now all broken again). I'm sure there's just a missing case somewhere. |
JuliaLang#58182) The point of JuliaLang#57979 was to make inference faster, but it made it instead much slower (JuliaLang@83524ac#commitcomment-155658124), so revert back to the fast behavior before it was "optimized" (and revert the bugfixes for the original commit).
JuliaLang#58203) Reverts JuliaLang#58182. The API changes were intentional and desirable. Let's figure out why nansoldier was upset and re-apply this. --------- Co-authored-by: Cédric Belmant <[email protected]>
JuliaLang#58182) The point of JuliaLang#57979 was to make inference faster, but it made it instead much slower (JuliaLang@83524ac#commitcomment-155658124), so revert back to the fast behavior before it was "optimized" (and revert the bugfixes for the original commit).
JuliaLang#58203) Reverts JuliaLang#58182. The API changes were intentional and desirable. Let's figure out why nansoldier was upset and re-apply this. --------- Co-authored-by: Cédric Belmant <[email protected]>
The point of #57979 was to make inference faster, but it made it instead much slower (83524ac#commitcomment-155658124), so revert back to the fast behavior before it was "optimized" (and revert the bugfixes for the original commit).
@nanosoldier
runbenchmarks("inference", vs=":master")