Official CPU/GPU inference framework from Microsoft for 1-bit (ternary, 1.58-bit) large language models, built on llama.cpp.
41.2K3.8KC++MITUpdated 3 months ago
#1-bit
Curated GitHub repositories related to 1-bit, with AI summaries and key stats.
Official CPU/GPU inference framework from Microsoft for 1-bit (ternary, 1.58-bit) large language models, built on llama.cpp.