Skip to content
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.

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

Chunked prefill support #797

Merged
merged 13 commits into from
Jul 29, 2024
Merged

Chunked prefill support #797

merged 13 commits into from
Jul 29, 2024

Conversation

hnyls2002
Copy link
Collaborator

Thank you for your contribution, we really appreciate it. The following instructions will help improve your pull request and make it easier to receive feedback. If there are any items you don't understand, don't worry. Just submit the pull request and ask the maintainers for help.

Motivation

Support chunked prefill.

Modification

  1. Add an --chunked-prefill-size parameter.
  2. Add an inflight request field in tp worker.

Checklist

  1. Ensure pre-commit pre-commit run --all-files or other linting tools are used to fix potential lint issues.
  2. Confirm that modifications are covered by complete unit tests. If not, please add more unit tests for correctness.
  3. Modify documentation as needed, such as docstrings or example tutorials.

@Ying1123 Ying1123 self-assigned this Jul 29, 2024
@hnyls2002
Copy link
Collaborator Author

Also thanks @vikranth22446 for his help with chunked prefill.

python/sglang/srt/server_args.py Outdated Show resolved Hide resolved
python/sglang/srt/server_args.py Outdated Show resolved Hide resolved
python/sglang/srt/server.py Show resolved Hide resolved
python/sglang/srt/managers/controller/tp_worker.py Outdated Show resolved Hide resolved
python/sglang/srt/server_args.py Outdated Show resolved Hide resolved
python/sglang/srt/server_args.py Outdated Show resolved Hide resolved
@hnyls2002 hnyls2002 merged commit 2ec39ab into main Jul 29, 2024
2 checks passed
@hnyls2002 hnyls2002 deleted the chunked-prefill branch July 29, 2024 09:21
Ying1123 added a commit that referenced this pull request Jul 29, 2024
@hnyls2002 hnyls2002 restored the chunked-prefill branch July 29, 2024 09:45
@hnyls2002 hnyls2002 mentioned this pull request Jul 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants