Skip to content

refactor with block for sampling parameter update #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
May 25, 2025
Merged

refactor with block for sampling parameter update #2

merged 2 commits into from
May 25, 2025

Conversation

zhaochenyang20
Copy link
Collaborator

Checklist Before Starting

  • Search for similar PR(s).

What does this PR do?

I updated serval comments and the with block usage. one question left in here:

        # The format of the model weights to be loaded.
        # TODO(chenyang): why we set `load_format` to `dummy`?

        # “auto” will try to load the weights in the safetensors format and
        # fall back to the pytorch bin format if safetensors format is not
        # available.
        # “pt” will load the weights in the pytorch bin format.
        # “safetensors” will load the weights in the safetensors format.
        # “dummy” will initialize the weights with random values, which is
        # mainly for profiling.
        # “bitsandbytes” will load the weights using bitsandbytes quantization.
        # “npcache” will load the weights in pytorch format and store a numpy
        # cache to speed up the loading.

@zhaochenyang20
Copy link
Collaborator Author

Well, I am cool with the load_format. But I think seldomly do we use dummy 😂

zyzshishui
zyzshishui reviewed May 25, 2025
View reviewed changes
verl/workers/rollout/sglang_rollout/sglang_rollout.py Outdated
non_pad_index = torch.nonzero(prompt_token_ids != pad_token_id, as_tuple=False)[0][0]
non_pad_index = torch.nonzero(prompt_token_ids != pad_token_id, as_tuple=False)[0][
0
]
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That's not graceful, plz roll back to single line

@zyzshishui zyzshishui merged commit 7be85f7 into refactor May 25, 2025
2 checks passed
zyzshishui pushed a commit that referenced this pull request May 27, 2025
@Bihan @peterschmidt85
Add dstack example (#2) (volcengine#1706)
54b2677 
Co-authored-by: Bihan  Rana <bihan@Bihans-MacBook-Pro.local>
Co-authored-by: peterschmidt85 <andrey.cheptsov@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@zyzshishui zyzshishui zyzshishui left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@zhaochenyang20 @zyzshishui