Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
active 2025-04-15 → 2026-03-24 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 344 days from 2025-04-15 to 2026-03-24. Pushes: 11 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 34 total, peak 5 in a day. Comments: 35 total, peak 9 in a day. Stars: 197 total, peak 36 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| wdrink | 41 | 11 | 0 | 20 |
| 2018211801 | 7 | 0 | 0 | 4 |
| uwGZQ | 5 | 0 | 0 | 2 |
| micky-li-hd | 5 | 0 | 0 | 3 |
| hyc9 | 3 | 0 | 0 | 1 |
| Yovecent | 2 | 0 | 0 | 1 |
| NTUYWANG103 | 2 | 0 | 0 | 1 |
| Redtides0 | 2 | 0 | 0 | 0 |
| Tomorrow1sanotherday | 2 | 0 | 0 | 0 |
| BigPeng | 1 | 0 | 0 | 0 |
| zghhui | 1 | 0 | 0 | 1 |
| dsn01 | 1 | 0 | 0 | 0 |
| wnqnxbb | 1 | 0 | 0 | 0 |
| weijinbao1998 | 1 | 0 | 0 | 0 |
| shijian2001 | 1 | 0 | 0 | 1 |
| syjmelody | 1 | 0 | 0 | 0 |
| xxxxmmmmmm | 1 | 0 | 0 | 1 |
| QiYao-Wang | 1 | 0 | 0 | 0 |
| DwanZhang-AI | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#35Yovecent2025-09-11 06:58How to run it in the cuda 11.8 enviroment?
- Issue comment#32Yovecent2025-09-11 06:56Missing Image Decoding in Non-VLLM Generation
- Issue#34dsn012025-08-08 05:59About training epochs
- Issue#33Tomorrow1sanotherday2025-07-27 08:44使用vllm加速 Daniel0724/SimpleAR-1.5B-SFT 生成图片時，会卡在 Using model weights format ['*.safetensors']
- Issue#32shijian20012025-07-21 18:58Missing Image Decoding in Non-VLLM Generation
- Issue#30wdrink2025-07-01 01:11请问这个环境配置怎么解决呀？
- Issue comment#31wdrink2025-07-01 01:00transformers version in GRPO env
- Issue#31Redtides02025-06-29 08:51transformers version in GRPO env
- Issue comment#29wdrink2025-06-20 15:57Encounter error at data_args.sequence_length
- Issue#29hyc92025-06-19 13:04Encounter error at data_args.sequence_length
- Issue#28Redtides02025-06-19 11:59How to train GRPO without vllm
- Issue#25wdrink2025-06-18 05:36Training stalls at torch.tensor(ids, device=device)
- Issue comment#25wdrink2025-06-18 05:36Training stalls at torch.tensor(ids, device=device)
- Issue comment#25wdrink2025-06-11 05:52Training stalls at torch.tensor(ids, device=device)
- Issue comment#24wdrink2025-06-11 04:49Trl vllm-server: invalid choice
- Issue comment#24wdrink2025-06-11 04:49Trl vllm-server: invalid choice
- Issue comment#27hyc92025-06-10 11:33Question about language ability degradation
- Issue#27hyc92025-06-10 11:33Question about language ability degradation
- Issue comment#27wdrink2025-06-10 06:14Question about language ability degradation
- Issue comment#25shijian20012025-05-26 14:03Training stalls at torch.tensor(ids, device=device)
- Issue comment#24wdrink2025-05-26 03:45Trl vllm-server: invalid choice
- Issue comment#25wdrink2025-05-26 03:43Training stalls at torch.tensor(ids, device=device)
- Issue#26wdrink2025-05-22 01:14Question about the ratio of short and long captions in your trainset?
- Issue comment#26wdrink2025-05-21 01:06Question about the ratio of short and long captions in your trainset?
- Issue#22wdrink2025-05-21 01:05About the effects of CFG
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 197 stars here means stars gained during the window, not the repo's star count.