PrototypeCommon
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…
- Owner
- Sandermage (personal account)
- Stars
- Stars: 133
- Forks
- Forks: 6
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Topics
- cudallm-inferenceqwenvllmspeculative-decodingtool-callingrtx-3090awqconsumer-gpugemma
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- Futureppo/typesafe_registerStars: 133PythonPrototype
- DaVarga/bs-arm64Stars: 133PythonPrototype
- aa1143/NamiAgentStars: 133PythonPrototype
- ntoll/workflowStars: 133PythonPrototype
- ericholscher/django-kongStars: 133PythonPrototype
- pkrumins/hacker-topStars: 133PythonPrototype