Tags
- 2:4 1
- AdaRound 1
- ai 1
- announcement 1
- BF16 1
- caveduck 1
- Compiler 2
- data types 1
- deep-learning 4
- fake-quantization 1
- floating-point 1
- FP16 1
- FP4 1
- FP8 1
- GPU 1
- Hadamard 1
- INT8 1
- K-Means 1
- KL-divergence 1
- Korean AI Chips 1
- Linear-Quantization 1
- ModernBERT 1
- MXFP4 1
- NPU 2
- NVIDIA 1
- On-device 2
- Optimal-Brain-Damage 1
- pruning 1
- PyTorch 4
- QAT 1
- quantization 4
- QuaRot 1
- Rebellions 1
- sparsity 1
- STE 1
- straight-through-estimator 1
- torch.compile 1
- Triton 1
- 아웃라이어 1
- 양자화 2