verl vs peft
Two of the top projects in Training and fine-tuning, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
verl
Reinforcement learning training library for LLM post-training with PPO and GRPO
peft
Python library for LoRA and other parameter-efficient fine-tuning of Transformers models
Verdict
verl ranks higher, 81 to 78. Of the 4 score parts we measure for both, verl leads on 2, peft on none and 2 are even.
- Adoptionverl leads by 6 points, 55 to 49.
- FreshnessEven at 100.
- MaintenanceEven at 88.
- Agent-readyverl leads by 15 points, 85 to 70: a wide gap.
Pick verl if you are
ML engineers running RL post-training of LLMs on GPU clusters
- Pluggable backends: FSDP/FSDP2/Megatron-LM for training, vLLM/SGLang/HF for rollout
- Many RL algorithms built in: PPO, GRPO, ReMax, RLOO, REINFORCE++
Pick peft if you are
ML engineers fine-tuning LLMs and diffusion models on limited GPU memory
- Adapter checkpoints are MBs instead of GBs; 19MB vs 11GB for T0_3B
- LoRA trained a 12B model (mt0-xxl) on one 80GB GPU where full finetuning ran out of memory
| What we compare | verl | peft |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 55, popular | 49, known |
| Freshness | 100, active | 100, active |
| Maintenance | 88, healthy | 88, healthy |
| Easy to run | Not scored for this kind | Not scored for this kind |
| Agent-ready | 85, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 23.9k | 21.8k |
| License | Apache-2.0 (permissive) | Apache-2.0 (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Oct 2026 |
| Language | Python | Python |
| Docker | Yes | Yes |
| GPU | Required | Optional |
| arm64 or Apple Silicon | Not stated | Mentioned |
verl
verl is the open-source implementation of the HybridFlow paper from ByteDance Seed. It runs RL and supervised fine-tuning for LLMs using FSDP, FSDP2 or Megatron-LM for training and vLLM, SGLang or HF Transformers for rollout generation. It covers PPO, GRPO, RLOO, ReMax and others, with multi-turn tool calling, VLM support and scaling to 671B models.
Who it is for: ML engineers running RL post-training of LLMs on GPU clusters
Strengths
- Pluggable backends: FSDP/FSDP2/Megatron-LM for training, vLLM/SGLang/HF for rollout
- Many RL algorithms built in: PPO, GRPO, ReMax, RLOO, REINFORCE++
- Scales to 671B models and hundreds of GPUs via expert parallelism
- Supports NVIDIA, AMD and Ascend hardware; LoRA RL to save memory
Weaknesses
- Needs multi-GPU clusters in practice; minimum hardware not stated in README
- Many algorithm recipes live in a separate verl-recipe repository and submodule
- Version-sensitive: README warns against vLLM 0.7.x and requires >=0.8.2
- Several features remain under verl/experimental until merged into the main library
- GPU required
- Docker
- Needs Ray, PyTorch, vLLM, SGLang, Megatron-LM
- Models: Qwen3.5, Qwen3, Qwen2.5, Qwen2.5-VL, Kimi-VL
peft
PEFT wraps a pretrained model with adapter methods such as LoRA, soft prompts and IA3 so only a small set of extra parameters is trained. Adapters are saved as small checkpoints (19MB versus 11GB for T0_3B in the README's example). It integrates with Transformers, Diffusers, Accelerate and TRL, and can be combined with quantization such as QLoRA.
Who it is for: ML engineers fine-tuning LLMs and diffusion models on limited GPU memory
Strengths
- Adapter checkpoints are MBs instead of GBs; 19MB vs 11GB for T0_3B
- LoRA trained a 12B model (mt0-xxl) on one 80GB GPU where full finetuning ran out of memory
- Integrates with Transformers, Diffusers, Accelerate and TRL; works with quantized base models
- Install with pip; get_peft_model wraps an existing model in a few lines
Weaknesses
- Library only: no training UI, scheduler or serving; training loop is your own or Trainer
- Transformers integration lacks some PEFT features, such as merging adapters into the base model
- Models without official support need manual config for target modules
- Memory figures in the README assume an A100 80GB with over 64GB CPU RAM
- GPU optional
- Docker
- Needs PyTorch, Transformers
- Models: LoRA, Soft prompts, IA3, QLoRA, Transformers models
More in Training and fine-tuning
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.