Record · corpus.blog/posts/01a0823d-891e-70d0-b8c7-ee627af2f41d

VeRL-Omni v0.2.0: Faster Diffusion RL and Stable Omni Training

vLLM Blog · published 20 August 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at vllm.ai Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 28
Words captured: 1,715

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

Announcing VeRL-Omni: Easy, Fast, and Stable RL Training for Diffusion and Omni-Modality Models Read at the source ↗

vllm.ai

https://github.com/verl-project/verl-omni

github.com

https://verl-omni.readthedocs.io/en/latest/start/rollout_batching.html

verl-omni.readthedocs.io

https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/diffusion_continuous_batching

docs.vllm.ai

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/qwen_image/run_qwen_image_ocr_lora.sh

github.com

https://wandb.ai/mikecheung/flow_grpo/runs/1vsrnhbd

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/qwen_image/run_qwen_image_ocr.sh

github.com

https://wandb.ai/andyzhou/VeRL-Omni-demo/runs/8p8y9olb

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/sd35/run_sd35_medium_ocr_lora_v1.sh

github.com

https://wandb.ai/mikecheung/flow_grpo/runs/h04p15jr

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/sd35/run_sd35_medium_ocr_lora_v1_separate_async.sh

github.com

https://api.wandb.ai/links/didan/kk5uxbmh

api.wandb.ai

https://wandb.ai/mikecheung/flow_grpo/runs/o7x44yrr

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/gspo_trainer/qwen3_omni/run_qwen3_omni_thinker_gspo_lora_v1.sh

github.com

https://wandb.ai/mikecheung/gspo/runs/j5mro1tn

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/gspo_trainer/qwen3_omni/run_qwen3_omni_thinker_gspo_lora_mmk12_v1.sh

github.com

https://wandb.ai/mikecheung/gspo/runs/2j8hxr36

wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/gspo_trainer/qwen3_omni/run_qwen3_omni_thinker_gspo_npu_avqa_v1.sh

github.com

https://github.com/verl-project/verl-omni/blob/main/examples/dpo_trainer/qwen3_omni/qwen3_omni/run_qwen3_omni_omni_preference_lora.sh

github.com

https://api.wandb.ai/links/didan/iumxl2zr

api.wandb.ai

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/ltx2/README.md

github.com

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/qwen_image_edit/README.md

github.com

https://github.com/verl-project/verl-omni/blob/main/examples/flowgrpo_trainer/bagel/README.md

github.com

https://verl-omni.readthedocs.io/en/latest/examples/flowgrpo_trainer_sd35_drm.html

verl-omni.readthedocs.io

https://verl-omni.readthedocs.io/en/latest/algo/flowdppo.html

verl-omni.readthedocs.io

https://github.com/verl-project/verl-omni/blob/main/examples/dancegrpo_trainer/README.md

github.com

https://verl-omni.readthedocs.io/en/latest/index.html

verl-omni.readthedocs.io

https://github.com/verl-project/verl-omni/blob/main/CONTRIBUTING.md

github.com