post-training-quantization
Tracked open-source repos tagged post-training-quantization, sorted by stars.
Related topics
Topics that frequently appear alongside post-training-quantization on the same repo.
Recent risers
Repos created in the last 90 days, tagged post-training-quantization.
No new repos tagged with this topic in the last 90 days.
- #1
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
★ 2,706+0Star change over the last 7 days - #2
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
★ 2,265-1Star change over the last 7 days - #3
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
★ 879-1Star change over the last 7 days - #4
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
★ 724+1Star change over the last 7 days
