SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Python2.23 k
19 小时前
#自然语言处理# [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Python650
3 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