Unverified50% confidenceFactExact time
llama.cpp is an MIT-licensed C/C++ reference runtime with GGUF format at its core, supporting Metal, CUDA, ROCm, and Vulkan.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Verifiedllama.cpp是一个纯C/C++实现的推理框架，支持CPU推理和极低比特量化（如4-bit、2-bit），可在笔记本电脑甚至树莓派上运行LLM71% similarVerifiedllama.cpp supports GPU acceleration backends including Metal, CUDA, Vulkan, and SYCL.70% similarVerifiedllama.cpp is a highly optimized C++ inference engine that supports Metal acceleration for Apple Silicon, CUDA acceleration for NVIDIA, and ROCm acceleration for AMD.70% similarVerifiedllama.cpp是由Georgi Gerganov开发的纯C/C++推理引擎，支持在纯CPU环境下运行大模型67% similarUnverifiedllama.cpp was introduced in early 2023 to run LLaMA models using only a CPU, and subsequently added support for hardware acceleration backends such as Metal, CUDA, and ROCm.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898228API
curl https://kongchang.com/api/v1/knowledge/claims/898228MCP
get_claim(id=898228)