Skip to content

Navigation Menu

Appearance settings

View all features
- BY COMPANY SIZE
  Enterprises
  Small and medium teams
  Startups
  Nonprofits
- BY USE CASE
  App Modernization
  DevSecOps
  DevOps
  CI/CD
  View all use cases
- BY INDUSTRY
  Healthcare
  Financial services
  Manufacturing
  Government
  View all industries
View all solutions
- EXPLORE BY TOPIC
  AI
  Software Development
  DevOps
  Security
  View all topics
- EXPLORE BY TYPE
  Customer stories
  Events & webinars
  Ebooks & reports
  Business insights
  GitHub Skills
- SUPPORT & SERVICES
  Documentation
  Customer support
  Community forum
  Trust center
  Partners
View all resources
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  Accelerator
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

NVIDIA-NeMo / RL Public

Notifications You must be signed in to change notification settings
Fork 276
Star 1.4k

Code
Issues 386
Pull requests 140
Discussions
Actions
Projects
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Security
Insights

feat: support top-p top-k in grpo#2053

Open

yuki-97 wants to merge 20 commits intomainNVIDIA-NeMo/RL:mainfrom

yukih/topp-topkNVIDIA-NeMo/RL:yukih/topp-topkCopy head branch name to clipboard

Conversation Commits20 (20)Checks Files changed

Open

feat: support top-p top-k in grpo#2053
yuki-97 wants to merge 20 commits intomainfrom
yukih/topp-topk

Commits

Commits on Mar 10, 2026

Reimplement top-p and top-k from #1578

zhandaz
authored and
yuki-97
committed
apply previous change in loss_function.py

yuki-97
and
zhandaz
committed
split to logits_sampling_utils.py
yuki-97
committed
move TrainingSamplingParams to setup
yuki-97
committed
add topp topk in LogprobsPostProcessor
yuki-97
committed
update megatron
yuki-97
committed
update need_top_k_or_top_p_filtering
yuki-97
committed
fix test
yuki-97
committed
apply filter prev_logprobs before compute_and_apply_seq_logprob_error_masking
yuki-97
committed
update megatron and dtensorv1, and fix unit test
yuki-97
committed
update nightly test
yuki-97
committed
make megatron worker respect to make_sequence_length_divisible_by
yuki-97
committed
fix unit test
yuki-97
committed
limit nightly test threshold
yuki-97
committed
remove default value and update top_k check
yuki-97
committed
address comments
yuki-97
committed
add doc
yuki-97
committed
add functional test
yuki-97
committed
fix unit test
yuki-97
committed
update threshold
yuki-97
committed

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.