Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
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
Resources
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
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
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
{{ message }}
NVIDIA-NeMo
RL
Repository navigation
Code
Issues
577
(577)
Pull requests
739
(739)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
156
(156)
Milestones
8
(8)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
739
(739)
Closed
2,887
(2,887)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
fix(timer): measure checkpoint_must_save_by from job start
#4811
·
jseppanen
opened
Oct 20, 2026
Contributor
·
4 tasks
·
·
2
fix(automodel): merge LoRA into refit weights under activation checkpointing
CI:Lfast
#4810
·
yuekaizhang
opened
Oct 20, 2026
Contributor
·
·
3
fix(trtllm): drop the srun launcher env in TRT-LLM Ray workers
#4809
·
shuyixiong
opened
Oct 20, 2026
Contributor
·
4 tasks done
·
·
1
cp:
fix(recipes): disable vLLM async scheduling for Qwen3.5-397B GRPO 4794
cherry-pick
CI:L0
#4808
·
svcnvidia-nemo-ci
opened
Oct 20, 2026
Contributor
·
·
2
cp: cherry-pick #3865 - perf(refit): use NCCL Reshard for all async MXFP8 recipes
CI:Lfast
#4807
·
seonjinn
opened
Oct 20, 2026
Contributor
·
·
2
cp: cherry-pick #3984 - fix(refit): release trainer memory before collective export
CI:Lfast
Documentation
#4806
·
seonjinn
opened
Oct 20, 2026
Contributor
·
·
2
cp: cherry-pick #3461 - perf(recipes): use FlashInfer TRT-LLM MoE for BF16
CI:Lfast
#4805
·
seonjinn
opened
Oct 20, 2026
Contributor
·
·
3
fix(checkpoint): rank NaN metrics last in top-k pruning and best selection
community-request
#4804
·
v0ropaev
opened
Oct 20, 2026
·
2 of 4 tasks
·
·
1
feat(dynamo): engine switch, Megatron engine config, and the engine seam
#4801
·
lauradang
opened
Oct 20, 2026
Contributor
·
3 of 4 tasks
·
·
1
docs: announce Beam 1.0 Day 0 support
#4799
·
jinzex
opened
Oct 19, 2026
·
·
1
feat(nemo-gym): retire capture ledgers NeMo RL is done with
CI:Lfast
#4798
·
ananthsub
opened
Oct 19, 2026
Contributor
·
3 of 4 tasks
·
·
5
fix(sglang): disable legacy Outlines disk cache by default
cherry-pick
CI:L1
#4797
·
chtruong814
opened
Oct 19, 2026
Contributor
·
4 tasks
·
·
9
feat(dynamo): Megatron prefill/decode engines under the SingleController
Documentation
#4796
·
lauradang
opened
Oct 19, 2026
Contributor
·
4 tasks
·
·
1
fix(vlm): add exact GELU override for Super vision encoder
Documentation
#4795
·
rohitrango
opened
Oct 19, 2026
Contributor
·
3 of 4 tasks
·
·
2
feat(gym): bump Gym and add a Super 3.5 Gym venv prefetch config
CI:L1
#4793
·
yfw
opened
Oct 19, 2026
Contributor
·
3 of 4 tasks
·
·
5
feat(megatron): MXFP8/NVFP4 zero train-gen mismatch on Megatron flashinfer backend
#4791
·
YigongQin
opened
Oct 19, 2026
Collaborator
·
4 tasks
·
·
1
perf(tests): cherry-pick CUDA graph recipe optimizations to main (#4569)
CI:Lfast
#4787
·
fujial-code
opened
Oct 19, 2026
Contributor
·
·
4
perf(recipes): use TE FusedAdam for MiniMax-M2.7 GRPO (fp32 second moment)
CI:Lfast
#4786
·
joyang-nv
opened
Oct 19, 2026
Member
·
·
3
feat(nvfp4): per-token NVFP4 rollout for Nemotron 3.5 Lightning
Documentation
#4785
·
zhangyimi
opened
Oct 19, 2026
Contributor
·
·
1
feat(single-controller): support dynamic sampling for streaming sampler
CI:Lfast
Documentation
#4784
·
RayenTian
opened
Oct 19, 2026
Contributor
·
3 of 4 tasks
·
·
3
fix(data): stop validation dataloader workers after a partial pass
CI:L0
#4783
·
zhangyimi
opened
Oct 19, 2026
Contributor
·
·
3
feat(timeline): collect end-to-end training timelines and add the collect-training timeline skills
#4782
·
shuyixiong
opened
Oct 19, 2026
Contributor
·
4 tasks
·
·
1
fix(async): clear active vLLM caches around weight refits
#4780
·
rohitrango
opened
Oct 18, 2026
Contributor
·
3 of 4 tasks
·
·
2
fix: forward checkpointing.pretrained_checkpoint in every algorithm setup
community-request
#4779
·
dijor0310
opened
Oct 18, 2026
·
4 tasks done
·
·
1
1
fix(sc): SWE PPO fixes for token capture and Megatron critic memory
CI:L1
Documentation
#4776
·
bg51717
opened
Oct 18, 2026
Member
·
4 tasks done
·
·
24
Previous
1
2
3
4
5
6
7
…
30
Next
You can’t perform that action at this time.