rameshchukka

icon indicating an email [email protected]

Results 37 comments of rameshchukka

How to set batch size with Bert

@pgmpablo157321

Fix broken link

@jenhaoyang CLA check still fails. If this [step ](https://docs.google.com/forms/d/e/1FAIpQLSd4gItNaxbm9okFroxJEUmkmPjAJ6YegNxmHRAq8f6Uv_SDyw/viewform)is not already done, can you check with [email protected] if your github id is associated with mlcommons github repos?

Resolve compilation bugs

@CaoZhongZ Can you send email to [email protected] for the CLA and copy [email protected].

[URGENT] RetinaNet mAP is 37.50% on main, 37.55% on r2.1 branch

@psyhtest Accuracy and Latency targets should be referred to Inference rules https://github.com/mlcommons/inference_policies/blob/master/inference_rules.adoc#411-constraints-for-the-closed-division. I am not sure it is appropriate to change the rules at this late without discussion. @tjablin Can...

[URGENT] RetinaNet mAP is 37.50% on main, 37.55% on r2.1 branch

This issue is resolved during v2.1 result review meetings.

RNN-T: enable batch decoder

@galv Can you please review the PR?

can't find model "tokenization"

@LukeIreland1 Are there any updates to this issue. If there are none, this issue will be closed next week.

Could you please provide a processed binary loader of the Terabyte dataset?

@mnaumovfb Can you please take a look at the issue and comment?

Could you please provide a processed binary loader of the Terabyte dataset?

We need Criteo to allow last day of logs to be preprocessed by mlcommons and shared with inference wg.

Large language model inference

Wait until the training WG make a proposal and then discuss