mirror PyTorch implementation for "Large Language Diffusion Models"
Python · active 2025-03-30 → 2026-06-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 453 days from 2025-03-30 to 2026-06-25. Pushes: 42 total, peak 8 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 40 total, peak 3 in a day. Comments: 90 total, peak 6 in a day. Stars: 1,169 total, peak 43 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 |
|---|---|---|---|---|
| NieShenRuc | 67 | 36 | 1 | 30 |
| Kamichanw | 7 | 0 | 1 | 5 |
| colinzhaoxp | 7 | 0 | 0 | 6 |
| nieshenx | 4 | 4 | 0 | 0 |
| maomaocun | 3 | 0 | 0 | 1 |
| MinseoJ123 | 3 | 0 | 0 | 2 |
| SIKAI-C | 3 | 0 | 0 | 2 |
| ZHZisZZ | 3 | 0 | 0 | 3 |
| XiangZhang-zx | 3 | 0 | 0 | 1 |
| deadlykitten4 | 3 | 0 | 0 | 2 |
| duterscmy | 2 | 0 | 0 | 1 |
| yyujinxin | 2 | 0 | 0 | 0 |
| Rachum-thu | 2 | 0 | 0 | 2 |
| yuanzhi-zhu | 2 | 0 | 0 | 1 |
| giladturok | 2 | 0 | 0 | 2 |
| SaturdayGenfo | 2 | 0 | 0 | 1 |
| Ss-scee | 2 | 0 | 0 | 1 |
| Hippogriff | 2 | 0 | 0 | 1 |
| xushaoxuan123 | 2 | 1 | 0 | 1 |
| Algolzw | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#130josesho2026-03-22 11:08AttributeError: 'LLaDAModelLM' object has no attribute 'all_tied_weights_keys'
- Pull request#124sean-lamont2026-02-06 05:09
- Issue#123viiika2026-02-04 07:47[Docs] Add PRISM test-time scaling recipe / reference for LLaDA-8B-Instruct in README
- Issue comment#119Kamichanw2026-01-22 14:56cpu memory OOM when using lm-eval to evaluate LLADA
- Issue comment#119duterscmy2025-12-25 03:38cpu memory OOM when using lm-eval to evaluate LLADA
- Issue#121Yuxuan3142025-12-24 15:44Unconditional Generation
- Issue comment#119X-Xia08282025-12-19 09:34cpu memory OOM when using lm-eval to evaluate LLADA
- Issue comment#103giladturok2025-12-17 02:27Problems when using lm_eval and calculating ppl
- Issue comment#62giladturok2025-12-17 01:48Is float64 necessary？
- Issue#119duterscmy2025-12-04 08:19cpu memory OOM when using lm-eval to evaluate LLADA
- Issue comment#103irondreamer2025-11-13 08:10Problems when using lm_eval and calculating ppl
- Issue comment#118xushaoxuan1232025-11-08 09:29Fixed module installation, testcase and added github action to run tests
- Issue comment#118Saranyapal212025-11-01 16:11Fixed module installation, testcase and added github action to run tests
- Issue comment#115SIKAI-C2025-10-31 14:38[Help Needed] mmengine.Config.fromfile() resolves wrong path for local configs
- Issue comment#115tonyckc2025-10-31 08:09[Help Needed] mmengine.Config.fromfile() resolves wrong path for local configs
- Issue comment#115SIKAI-C2025-10-30 18:08[Help Needed] mmengine.Config.fromfile() resolves wrong path for local configs
- Issue comment#112Algolzw2025-10-28 17:44Evaluation is too slow
- Issue comment#112NieShenRuc2025-10-28 05:50Evaluation is too slow
- Pull request#116seungjae50442025-10-25 03:30
- Issue#115SIKAI-C2025-10-24 20:35[Help Needed] mmengine.Config.fromfile() resolves wrong path for local configs
- Issue comment#107mli7462025-10-24 04:17Update the WeChat QR code
- Issue comment#76Gertlek2025-10-15 11:45generate: skip unnecessary unmask steps and warn user about it
- Issue comment#71Chenfeng12712025-10-02 01:50Stucked when running evaluation.
- Issue#113MengAiDev2025-10-01 23:53Failed to finetune llada moe with math competition dataset
- Issue#112Algolzw2025-09-30 11:01Evaluation is too slow
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,169 stars here means stars gained during the window, not the repo's star count.