Cuda · MIT
kindlingai/gr8
A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash
★ 64
Stars
13 forks · 54 open issues
+2.1/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
29.8
Momentum / 100
see the breakdown below
29d ago
Created
last push 1h ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 9.5 | +2.1/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 15.0 | last push 1h ago; decays to zero at 180 days |
| Scale | 15 | 5.3 | 64 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 29.8 | sum of the above |
Detail
| Topics | cudadeepseekdgx-sparkgb10glminference-enginellm-inferencerdmatensor-parallel |
| Matched on | LLM & Inference (llm-inference) |
| Short window | no snapshot 5–10 days old yet |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 2.15 stars/day over 30 days |
| First seen here | 2026-11-07 |
| Last read | 1h ago |