Python · Apache-2.0
Leonccaa/ReVolta
Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/disk KV offload, and MTP or DFlash2 speculative decoding.
★ 49
Stars
2 forks · 9 open issues
+2.4/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
30.1
Momentum / 100
see the breakdown below
20d ago
Created
last push 3h ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 10.2 | +2.4/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 3h ago; decays to zero at 180 days |
| Scale | 15 | 4.9 | 49 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 30.1 | sum of the above |
Detail
| Topics | awqflash-nextkv-cache-offloadingllm-inferencenvfp4nvidia-v100qwenqwen3-8qwen3-8-flash-nextsm70tesla-v100v100vllmvolta |
| 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 | 2.40 stars/day over 20 days |
| First seen here | 2026-11-06 |
| Last read | 3h ago |