MoH: Multi-Head Attention as Mixture-of-Head Attention
active 2024-10-09 → 2026-03-31 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 539 days from 2024-10-09 to 2026-03-31. Pushes: 11 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 10 total, peak 3 in a day. Comments: 10 total, peak 3 in a day. Stars: 280 total, peak 31 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 |
|---|---|---|---|---|
| jpthu17 | 19 | 11 | 0 | 7 |
| tisgotos | 3 | 0 | 0 | 0 |
| p1nksnow | 3 | 0 | 0 | 2 |
| TreasureHunter | 1 | 0 | 0 | 0 |
| Miocio-nora | 1 | 0 | 0 | 0 |
| wxxhaoshuai | 1 | 0 | 0 | 0 |
| IsNoobgrammer | 1 | 0 | 0 | 1 |
| Frfr58nancesWhm7oite | 1 | 0 | 0 | 0 |
| arringtonjohngk-75 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#7IsNoobgrammer2025-05-20 09:59About KV-Cache
- Issue#7Miocio-nora2025-04-17 10:25About KV-Cache
- Issue comment#6jpthu172025-04-16 09:49Confusion about the weight gi
- Issue#6TreasureHunter2025-04-13 06:14Confusion about the weight gi
- Issue comment#4jpthu172025-03-25 10:23关于项目的异常增长：刷 Star 的问题？
- Issue#5Frfr58nancesWhm7oite2025-03-25 06:21Unusual Spike in GitHub Stars — Suspected Artificial Boosting
- Issue#4arringtonjohngk-752025-03-25 04:59关于项目的异常增长：刷 Star 的问题？
- Issue comment#3jpthu172025-03-24 04:08About NaN
- Issue#3wxxhaoshuai2025-03-12 06:38About NaN
- Issue#2tisgotos2024-12-30 13:54Visualization of the head load distribution
- Issue#2tisgotos2024-12-30 13:14Visualization of the head load distribution
- Issue#2tisgotos2024-12-30 11:25Visualization of the head load distribution
- Issue#1jpthu172024-10-31 07:17The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1jpthu172024-10-23 09:14The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1p1nksnow2024-10-23 03:00The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1jpthu172024-10-22 13:09The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1p1nksnow2024-10-22 10:02The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1jpthu172024-10-22 03:54The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue comment#1jpthu172024-10-20 13:01The checkpoint of MoH-LLaMA3-8B in HF is 404.
- Issue#1p1nksnow2024-10-20 03:03The checkpoint of MoH-LLaMA3-8B in HF is 404.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 280 stars here means stars gained during the window, not the repo's star count.