Sass · Apache-2.0
kacper-daftcode/vLLM-Moet
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
★ 568
Stars
50 forks · 0 open issues
+4.0/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
36.3
Momentum / 100
see the breakdown below
4mo ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 13.3 | +4.0/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 3d ago; decays to zero at 180 days |
| Scale | 15 | 8.0 | 568 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 36.3 | sum of the above |
Detail
| Topics | blackwellcudadeepseekllm-inferencemoertx-5090rtx-pro-6000sasssm120vllm |
| 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 | 3.98 stars/day over 143 days |
| First seen here | 2026-11-04 |
| Last read | 2d ago |