IBM / text-generation-inference

IBM development fork of https://github.com/huggingface/text-generation-inference
Apache License 2.0
52 stars 30 forks source link

Speculative decoding #74

Closed prashantgupta24 closed 5 months ago

prashantgupta24 commented 5 months ago

Motivation

[Describe why this change is needed]

Modifications

[Describe the code changes]

Result

[Describe how the changes affects existing behavior and how to test it]

Related Issues

[Resolves #123]

tdoublep commented 5 months ago

@prashantgupta24 can we please move this out of draft and request review from @njhill ?

prashantgupta24 commented 5 months ago

@tdoublep @JRosenkranz we'll have to fix the DCO for this branch, also update the description (info for the DCO - https://github.com/IBM/text-generation-inference/pull/74/checks?check_run_id=23555318238)

prashantgupta24 commented 5 months ago

closing in favor of https://github.com/IBM/text-generation-inference/pull/78