High-efficiency floating-point neural network inference operators for mobile, server, and Web
7 daysStars2.4k24h gain-Score0.0
Search
Find trending repositories by name or description.
3 results for “high-efficiency”
Find trending repositories by name or description.
High-efficiency floating-point neural network inference operators for mobile, server, and Web
High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.