Python · Apache-2.0
Elevatormusic/DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark
DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.
★ 76
Stars
10 forks · 17 open issues
+5.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
24.9
Momentum / 100
see the breakdown below
21d ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 4.5 | +5.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.34× the monthly pace |
| Freshness | 15 | 15.0 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 5.5 | 76 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 24.9 | sum of the above |
Detail
| Topics | deepseekdgx-sparkexl3gb10llm-inferencenvidiatensor-paralleltensorfold |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +5 stars over 7 days = 0.7/day |
| Long window | +34 stars over 16 days = 2.1/day |
| Lifetime average | 4.11 stars/day over 18 days |
| First seen here | 2026-10-20 |
| Last read | 2d ago |