BitCPM-CANN
PulseAugur coverage of BitCPM-CANN — every cluster mentioning BitCPM-CANN across labs, papers, and developer communities, ranked by signal.
-
New low-bit and ternary AI models released with performance updates · 1 source tracked
Several new low-bit and ternary models have been released and are being tracked, including Bonsai's 1-bit and 1.58-bit (ternary) versions, with a 27B parameter model now running on mainline backends. Updates to llama.cp…
-
Bingbi AI releases BitCPM-CANN for 1.58-bit training on domestic hardware
Bingbi AI has open-sourced BitCPM-CANN, a training framework designed for domestic AI accelerators. This framework enables 1.58-bit model training, which reportedly reduces inference memory requirements by up to six tim…
-
New 1.58-bit LLM family achieves 6x inference memory reduction
A new family of large language models, BitCPM-CANN, has been developed using a novel 1.58-bit ternary quantization technique. These models, ranging from 0.5B to 8B parameters, achieve significant memory reduction for in…