NVIDIA-NeMo / NVIDIA-NeMo/RL

Megatron Inference does not support post-processed logprob return

Open
#2,852 0 comments 0 reactions 1 assignee Claimed by @terrykong View on GitHub
bug Feature
Dominant language
Python
Stars
2k
Forks
561
Avg merge
4d 5h
Merged PRs (30d)
145

Description

**Describe the bug**

Once Megatron Inference gains a `logprobs-mode` argument, [71da32a9863780a7f85ca3084219ce66357b8925](https://github.com/NVIDIA-NeMo/RL/commit/71da32a9863780a7f85ca3084219ce66357b8925) must be reverted.

**Steps/Code to reproduce bug**

Please list *minimal* steps or code snippet for us to be able to reproduce the bug.

A helpful guide on on how to craft a minimal bug report http://matthewrocklin.com/blog/work/2018/02/28/minimal-bug-reports.

**Expected behavior**

A clear and concise description of what you expected to happen.

**Additional context**

Add any other context about the problem here.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.