Skip to content

Issues: volcengine/verl

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

33 Open 39 Closed
33 Open 39 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Can we use VeRL to train the reward models
#197 opened Feb 4, 2025 by YSLIU627
Integrate Verl with 🤗 hub
#190 opened Feb 3, 2025 by NielsRogge
1
1
"AssertionError: Expects tensor to be on the compute device cuda:0, was on cpu" for fsdp
#181 opened Feb 1, 2025 by bebetterest
2
if rollout.n is doubled, will the samples used for training doubled too?
#180 opened Feb 1, 2025 by StarDewXXX
3
[Question] Is vLLMRollout.generate_sequences the right place to implement tool calling? enhancement New feature or request question Further information is requested vllm related
#176 opened Jan 31, 2025 by accupham
6
Add a format issue template
#172 opened Jan 30, 2025 by vermouth1992
Add nightly ci to ensure accuracy
#171 opened Jan 30, 2025 by vermouth1992
Mulit-modal rl training support?
#168 opened Jan 30, 2025 by lucasjinreal
3
Add assertion to ensure the reward in GRPO is generated by ORM
#160 opened Jan 29, 2025 by vermouth1992
@PeterSH6
Any support for peft methods on PPO?
#159 opened Jan 29, 2025 by HaochenZhao
7
Example for running verl jobs on slurm managed cluster?
#158 opened Jan 29, 2025 by qiuhuida
7
feature request: support llama3 rope_scaling type?
#155 opened Jan 28, 2025 by qiuhuida
Union problem when n>1 and sampling for val data
#148 opened Jan 27, 2025 by chujiezheng
1
Additional memory optimization features
#144 opened Jan 27, 2025 by SalmanMohammadi
1
Does verl support Breakpoint retraining ？
#143 opened Jan 27, 2025 by DavideHe
3
feature request: support different versions of vllm
#106 opened Jan 15, 2025 by Cppowboy
5
Fused CE loss integration help wanted Extra attention is needed
#97 opened Jan 12, 2025 by eric-haibin-lin
1
Liger kernel integration help wanted Extra attention is needed
#96 opened Jan 12, 2025 by eric-haibin-lin
4
Resume from checkpoints
#76 opened Jan 4, 2025 by fzyzcjy
2
Question about actor training-rollout resharding
#73 opened Jan 2, 2025 by 0oshowero0
2
Support RLOO/GRPO/REINFORCE?
#68 opened Dec 31, 2024 by fzyzcjy
24
Actor model didn't update correctly when upgrade megatron to core-r0.6.0
#64 opened Dec 24, 2024 by Wodswos
7
Does this framework support full parameter PPO tuning for the Qwen2.5-14B model on 8-A100 GPUs with 80GB memory each?
#40 opened Dec 7, 2024 by hljjjmssyh
1
enable_gradient_checkpointing is not working
#26 opened Nov 27, 2024 by Vamix
2
Unexpected Increase in Rollout Time After Reducing num_hidden_layers in deepseek-llm-7b-chat Model
#24 opened Nov 25, 2024 by metaqiang
2
ProTip! Find all open issues with in progress development work with linked:pr.