Python
JinjieNi/MegaDLMs
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
★ 343
Stars
35 forks · 3 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
7.4
Momentum / 100
see the breakdown below
12mo ago
Created
last push 12mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 0.0 | last push 12mo ago; decays to zero at 180 days |
| Scale | 15 | 7.4 | 343 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 7.4 | capped at 35 because growth is unmeasured |
Detail
| Topics | diffusionlarge-language-models |
| Matched on | LLM & Inference (large-language-models) |
| Short window | no snapshot 5–10 days old yet |
| Long window | +0 stars over 26 days = 0.0/day |
| Lifetime average | 0.91 stars/day over 375 days |
| First seen here | 2026-10-11 |
| Last read | 14d ago |