An edge-native MoE serving engine that runs large open-weight models like DeepSeek-V4 and Qwen3.6 on consumer GPUs and CPUs.
14.6K1.5KPythonApache-2.0Updated 9 hours ago
#llm-serving
Open-source projects tagged “llm-serving”
Curated GitHub repositories related to llm-serving, with AI summaries and key stats.