TensorFlow: “SOTA lowbit LLM quantization INT8FP8INT4FP4NF4 sparsity leading model…”

TensorFlow @tensorflowblog · 1.34K subscribers

Post #450 2.36K Mar 16, 2024, 09:27 UTC

SOTA lowbit LLM quantization INT8FP8INT4FP4NF4 sparsity leading model compression techniques on TensorFlow PyTorch and ONNX Runtime

View on Github.com

GitHub GitHub - intel/neural-compressor: SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression… SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime - intel/neural-compressor

Open in Telegram All posts from @tensorflowblog