multiple PredictionEventHandler #1392
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…path for hypothetical async setup this may be appealing if your setup uses async heavily for e.g. downloading weights and also doing something else Signed-off-by: technillogue <technillogue@gmail.com>
Signed-off-by: technillogue <technillogue@gmail.com>
… in setup running the worker tests individually is always fine, but sometimes when running the full suite the same loop test throws "Unreliable test timings! On an initial run, this test took 652.54ms, which exceeded the deadline of 500.00ms, but on a subsequent run it took 346.94 ms" Signed-off-by: technillogue <technillogue@gmail.com>
technillogue
force-pushed
the
syl/jank-batch
branch
2 times, most recently
from
5cae7f7
to
34d05af
Compare
Signed-off-by: technillogue <technillogue@gmail.com>
technillogue
force-pushed
the
syl/jank-batch
branch
from
34d05af
to
6bac76a
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
stacked
#1352#1366we agreed to have a separate release channel for llama, so we can postpone making this compatible with non-batched releases as long as we'll be able to do it later.
this PR tries to start getting at the core problem of handling multiple predictions.