Flex Wang

neeva.com

Results 5 comments of


                                            Flex Wang

Error: The security token included in the request is invalid - when AWS key/secret changes between GHA jobs

+1

[BUG] Add support for pull request close event with merge set to true

> @a123775 @flexwang2 This has been resolved in the latest release. Thanks a lot bro!

Splitting a batch to max_batch_size if the batch size is larger than max_batch_size

We would like to see this chunkation on trition side feature will go live

Can I enable streaming on an ensemble model?

Answer is yes

flashattention only enabled for gpt-styled models

@byshiue can I know why we don't use flash attention for encoder model as well?