SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Python2.26 k
3 天前
C1.46 k
10 天前
#计算机科学#Machine Learning Framework for Operating Systems - Brings ML to Linux kernel
翻译 - 操作系统的机器学习框架 - 将机器学习引入 Linux 内核
C153
3 年前