Python · Apache-2.0
Sandermage/sndr_core_engine
SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.
★ 133
Stars
6 forks · 25 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
18.2
Momentum / 100
see the breakdown below
6mo ago
Created
last push 38d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 12.0 | last push 38d ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 133 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.2 | sum of the above |
Detail
| Topics | awqconsumer-gpucudagemmakv-cache-quantizationllm-inferencellm-servinglocal-llmmemorypgvectorquantizationqwenragrtx-3090rtx-4090self-hostedspec-decodespeculative-decodingtool-callingvllm |
| Matched on | LLM & Inference (llm-inference, llm-serving) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +0 stars over 26 days = 0.0/day |
| Lifetime average | 0.66 stars/day over 202 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |