mini-verl

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

DaoyuanLi2816/mini-verl

View on GitHub ↗

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

mini-verl grew +2.0% in the last 30 days, ranks 190th of 370 in Training Toolkits, last commit 68 days ago.

Star trajectory

82 days tracked
2026-08-31313 stars today2026-11-22
Momentum

+2.0% in 30d, above the Training Toolkits median of +0.3%.

Maintenance

Last commit 68 days ago, fresher than the median of 199.5d.

How it compares in Training Toolkits

mini-verl
313
stars
+2.0% 30d
commit 68 days ago
Training Toolkits median
320
stars
+0.3% 30d
commit ~199.5d ago
Leader · TTS
46.3k
stars
+0.3% 30d
commit 827 days ago

Ranked 190th of 370 by stars.

Ranked by shared tags, then keywords, then stars
  1. Halo is an open-source framework built by White Circle for training large language and multimodal models

    +34 (+4.1%) in 30d · Committed today · Python · Other license

    Shares Training Toolkits, Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF

  2. The official implementation of Self-Play Preference Optimization (SPPO)

    +1 (+0.2%) in 30d · Committed 668d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Fine-Tuning (LoRA / PEFT), Training Toolkits

  3. LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)

    +0 (+0.0%) in 30d · Committed 1,137d ago · Python

    Shares Training Toolkits, Reinforcement Learning / RLHF, Fine-Tuning (LoRA / PEFT)

  4. [NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs…

    +7 (+1.9%) in 30d · Committed 211d ago · Python · MIT

    Shares Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF, Training Toolkits

  5. Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning…

    +30 (+14%) in 30d · Committed 11d ago · Python · Apache-2.0

    Shares Fine-Tuning (LoRA / PEFT), Training Toolkits, Reinforcement Learning / RLHF

  6. A framework for agentic tool use training with reinforcement learning

    +1 (+0.5%) in 30d · Committed 228d ago · Python

    Shares Reinforcement Learning / RLHF, Fine-Tuning (LoRA / PEFT), Training Toolkits

  7. chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu

    +0 (+0.0%) in 30d · Committed 1,185d ago · Python · Apache-2.0

    Shares Fine-Tuning (LoRA / PEFT), Training Toolkits, Reinforcement Learning / RLHF

  8. An algorithm-focused interface for common llm training, continual learning, and reinforcement learning…

    +3 (+2.9%) in 30d · Committed 9d ago · Python · Apache-2.0

    Shares Fine-Tuning (LoRA / PEFT), Training Toolkits, Reinforcement Learning / RLHF

  9. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Training Toolkits, Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF

  10. From-scratch PyTorch replications of classic and SOTA AI/ML papers: transformers, attention, GANs, diffusion…

    Committed 17d ago · Jupyter Notebook · Apache-2.0

    Shares Training Toolkits, Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF

Language
Python
License
Apache License 2.0
Contributors
1
Forks
75
Watchers
53
Open issues
1
Releases
28
Created
2026-07-27
Stars this week
+2

You've seen where mini-verl stands today.

Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain mini-verl?

Claim this page to add your own call-to-action.

Claim this page