Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
active 2024-04-12 → 2026-04-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 727 days from 2024-04-12 to 2026-04-08. Pushes: 52 total, peak 22 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 35 total, peak 6 in a day. Comments: 73 total, peak 15 in a day. Stars: 355 total, peak 26 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 |
|---|---|---|---|---|
| Beomi | 91 | 52 | 4 | 24 |
| Lazy3valuation | 14 | 0 | 0 | 8 |
| DavideHe | 8 | 0 | 0 | 6 |
| jlamprou | 7 | 0 | 0 | 5 |
| LWL-cpu | 7 | 0 | 0 | 7 |
| 18140663659 | 3 | 0 | 0 | 2 |
| ictzyqq | 3 | 0 | 0 | 2 |
| LzhinFdu | 3 | 0 | 0 | 2 |
| WF0511 | 3 | 0 | 0 | 2 |
| pengshuang | 2 | 0 | 0 | 2 |
| lihua8848 | 2 | 0 | 0 | 2 |
| huyufeng0407 | 2 | 0 | 0 | 1 |
| fyang064 | 2 | 0 | 0 | 1 |
| raghavgarg97 | 2 | 0 | 0 | 1 |
| zzr-idam | 2 | 0 | 0 | 1 |
| a1exyu | 2 | 0 | 0 | 1 |
| zeyuliu1037 | 1 | 0 | 0 | 0 |
| ZackZikaiXiao | 1 | 0 | 0 | 1 |
| DewEfresh | 1 | 0 | 0 | 0 |
| Thirvin | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#28zeyuliu10372024-11-19 20:08Question related to the loss calculation
- Issue comment#17rithik252024-09-26 19:30Are there any trained InfinityTransformer weights available?
- Issue comment#23lihua88482024-08-23 09:33About memory missing location information
- Issue comment#23pengshuang2024-07-25 12:19About memory missing location information
- Issue comment#23LzhinFdu2024-07-25 09:59About memory missing location information
- Issue comment#23pengshuang2024-07-25 09:32About memory missing location information
- Issue comment#26HUST-Keep-Lin2024-07-11 07:22Issue while runing test_train.small.gemma.infini.py
- Issue comment#27Liuzirui6662024-07-03 05:56Support Zero-3?
- Issue comment#21LWL-cpu2024-06-27 16:41mem and norm_term is nan？
- Issue comment#21LWL-cpu2024-06-27 16:22mem and norm_term is nan？
- Issue comment#21DavideHe2024-06-27 15:06mem and norm_term is nan？
- Issue comment#21LWL-cpu2024-06-27 15:00mem and norm_term is nan？
- Issue comment#21DavideHe2024-06-27 11:41mem and norm_term is nan？
- Issue comment#21DavideHe2024-06-27 11:35mem and norm_term is nan？
- Issue comment#21WF05112024-06-27 11:24mem and norm_term is nan？
- Issue comment#21LWL-cpu2024-06-27 11:24mem and norm_term is nan？
- Issue comment#21WF05112024-06-25 07:35mem and norm_term is nan？
- Issue#27WF05112024-06-25 06:39Support Zero-3?
- Issue comment#20lihua88482024-06-25 06:32Segment and block size error
- Issue comment#21DavideHe2024-06-18 09:33mem and norm_term is nan？
- Issue comment#26raghavgarg972024-06-18 09:23Issue while runing test_train.small.gemma.infini.py
- Issue comment#21LWL-cpu2024-06-18 04:48mem and norm_term is nan？
- Issue comment#25LWL-cpu2024-06-17 02:55Model loses information very quickly
- Issue#26raghavgarg972024-06-15 11:18Issue while runing test_train.small.gemma.infini.py
- Issue comment#25Thirvin2024-06-06 04:37Model loses information very quickly
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 355 stars here means stars gained during the window, not the repo's star count.