You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Would it be possible to fix tensor parallel > 1 with AWQ and GPTQ before the new release? I’m seeing about 5 people reporting now that it’s broken (most seem to mention Mixtral)
ETA: Jan 3rd - 4th
Major changes
TBD
PRs to be merged before the release
tensor parallel MOE implementation #2293(deferred)The text was updated successfully, but these errors were encountered: