Python · Apache-2.0
chadhurley25075-png/pd-bridge
Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE
★ 151
Stars
13 forks · 2 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
20.8
Momentum / 100
see the breakdown below
2mo ago
Created
last push 22d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 13.4 | last push 22d ago; decays to zero at 180 days |
| Scale | 15 | 6.3 | 151 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 20.8 | sum of the above |
Detail
| Topics | apple-silicondeepseekdgx-sparkheterogeneous-inferencekv-cachellm-inferencemlxomlxprefill-decodevllm |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +1 stars over 26 days = 0.0/day |
| Lifetime average | 2.53 stars/day over 60 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |