2 results found Sort:

intel
neural-compressor intel
258
2.3k
apache-2.0
33
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
awq fp4 gptq int4 int8 pruning mxformat sparsity sparsegpt auto-tuning smoothquant quantization low-precision large-language-models knowledge-distillation post-training-quantization quantization-aware-training
Created 2020-07-21
3,699 commits to master branch, last one 2 days ago
Tiiiger
QPyTorch Tiiiger
74
268
mit
12
Low Precision Arithmetic Simulation in PyTorch
learning low-precision
Created 2018-07-30
246 commits to master branch, last one 7 months ago