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
#自然语言处理#[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Python661
4 个月前
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
#自然语言处理#[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization