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.
Sandermage/sndr_core_engine
View on GitHub ↗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.
sndr_core_engine grew +0.8% in the last 30 days, ranks 230th of 303 in Inference Optimization, last commit 24 days ago.
Star trajectory
115 days tracked+0.8% in 30d, below the Inference Optimization median of +1.5%.
Last commit 24 days ago, staler than the median of 15d.
How it compares in Inference Optimization
Ranked 230th of 303 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 2
- Forks
- 5
- Watchers
- 4
- Open issues
- 5
- Releases
- 2
- Created
- 2026-04-17
- Stars this week
- +0
You've seen where sndr_core_engine stands today.
Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.