fp4 topic
List
fp4 repositories
neural-compressor
2.0k
Stars
241
Forks
24
Watchers
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
neural-speed
273
Stars
31
Forks
Watchers
An innovative library for efficient LLM inference via low-bit quantization