Quantization in Depth
- IntroductionVideo・4 mins
- OverviewVideo・3 mins
- Quantize and De-quantize a TensorVideo with Code Example・11 mins
- Get the Scale and Zero PointVideo with Code Example・12 mins
- Symmetric vs Asymmetric ModeVideo with Code Example・7 mins
- Finer Granularity for more PrecisionVideo with Code Example・2 mins
- Per Channel QuantizationVideo with Code Example・11 mins
- Per Group QuantizationVideo with Code Example・7 mins
- Quantizing Weights & Activations for InferenceVideo with Code Example・3 mins
- Custom Build an 8-Bit QuantizerVideo with Code Example・13 mins
- Replace PyTorch layers with Quantized LayersVideo with Code Example・5 mins
- Quantize any Open Source PyTorch ModelVideo with Code Example・8 mins
- Load your Quantized Weights from HuggingFace HubVideo with Code Example・7 mins
- Weights PackingVideo・5 mins
- Packing 2-bit WeightsVideo with Code Example・8 mins
- Unpacking 2-Bit WeightsVideo with Code Example・8 mins
- Beyond Linear QuantizationVideo・7 mins
- ConclusionVideo・1 min