Official implementation of TransNormerLLM: A Faster and Better LLM
active 2023-08-15 → 2025-10-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 807 days from 2023-08-15 to 2025-10-29. Pushes: 24 total, peak 11 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 12 total, peak 2 in a day. Comments: 29 total, peak 6 in a day. Stars: 112 total, peak 5 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 |
|---|---|---|---|---|
| XuyangShen | 21 | 14 | 0 | 7 |
| Doraemonzzz | 16 | 2 | 0 | 12 |
| liddalidd | 4 | 4 | 0 | 0 |
| XintianHan | 4 | 0 | 0 | 3 |
| weigao266 | 4 | 4 | 0 | 0 |
| Hanshifancoder | 4 | 0 | 0 | 3 |
| Leopold2333 | 3 | 0 | 0 | 1 |
| relic-yuexi | 3 | 0 | 0 | 1 |
| redbrain | 2 | 0 | 2 | 0 |
| janEbert | 1 | 0 | 0 | 0 |
| waneon | 1 | 0 | 0 | 0 |
| iminfine | 1 | 0 | 0 | 0 |
| wangyuxin87 | 1 | 0 | 0 | 0 |
| OpenNLPLab123 | 1 | 0 | 0 | 1 |
| ChuanhongLi | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#12Leopold23332024-11-29 01:33Confusions about the decay parameter λ
- Issue#12Leopold23332024-11-29 01:33Confusions about the decay parameter λ
- Issue comment#12Doraemonzzz2024-11-28 10:34Confusions about the decay parameter λ
- Issue#12Leopold23332024-11-28 10:09Confusions about the decay parameter λ
- Issue comment#11Hanshifancoder2024-11-01 06:29Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue comment#11Doraemonzzz2024-11-01 06:25Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue comment#11Hanshifancoder2024-11-01 06:19Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue comment#11Doraemonzzz2024-11-01 03:33Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue comment#11Hanshifancoder2024-11-01 03:28Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue comment#11Doraemonzzz2024-10-31 15:35Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue#11Hanshifancoder2024-10-31 10:43Differences between Lightning Attention1 and Lightning Attention2 code implementations
- Issue#10Doraemonzzz2024-04-01 07:27This is not a linear attention transformer.
- Issue comment#10Doraemonzzz2024-04-01 07:16This is not a linear attention transformer.
- Issue#10iminfine2024-04-01 07:07This is not a linear attention transformer.
- Issue comment#9Doraemonzzz2024-01-25 13:22Bugs in Triton operator?
- Pull request#5redbrain2024-01-24 15:08
- Issue comment#8Doraemonzzz2024-01-24 08:22Benchmark results can not be reproduced
- Issue#8waneon2024-01-24 08:16Benchmark results can not be reproduced
- Issue comment#7XuyangShen2024-01-23 05:00你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue comment#7ChuanhongLi2024-01-23 03:36你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue#7relic-yuexi2024-01-12 09:44你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue comment#7OpenNLPLab1232024-01-12 03:58你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue comment#7relic-yuexi2024-01-12 01:58你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue comment#7XuyangShen2024-01-11 13:25你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
- Issue comment#7XuyangShen2024-01-11 07:06你好，请问各个参数量的模型默认加载使用会占用多少显存？不同max_new_tokens大概会要占用多少显存？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 112 stars here means stars gained during the window, not the repo's star count.