Official inference framework for 1-bit LLMs
Pulse
62
Velocity
+145%
Stars
37,051
Official framework for efficient 1-bit Large Language Models.
Enables highly efficient inference for 1-bit Large Language Models.
Run LLMs with drastically reduced memory and compute costs.
Why Trending
Pioneers efficient 1-bit LLM inference for reduced compute.
Target Audience
Researchers and engineers working with LLMs.
Similar Projects