2024-01-11_neural-network-quantization-and-number
Canonical Target Counts
| Target | Occurrences |
|---|
| 04_knowledge_base/FP8 | 15 |
| 04_knowledge_base/INT8 | 11 |
| 02_companies/NVDA | 10 |
| 04_knowledge_base/Quantization | 10 |
| 04_knowledge_base/Microscaling | 8 |
| 04_knowledge_base/FP32 | 7 |
| 04_knowledge_base/FP16 | 7 |
| 02_companies/MSFT | 6 |
| 02_companies/GOOG | 5 |
| 02_companies/QCOM | 5 |
| 02_companies/AMD | 4 |
| 02_companies/META | 4 |
| 04_knowledge_base/BF16 | 4 |
| 02_companies/INTC | 3 |
| 04_knowledge_base/DRAM | 2 |
| 04_knowledge_base/Post-training | 2 |
| 02_companies/Aligned Data Centers | 2 |
| 04_knowledge_base/MXINT8 | 2 |
| 04_knowledge_base/Block Floating Point | 2 |
| 04_knowledge_base/CPU | 2 |
| 04_knowledge_base/MXFP4 | 2 |
| 04_knowledge_base/PyTorch | 1 |
| 02_companies/Together AI | 1 |
| 04_knowledge_base/H100 | 1 |
| 04_knowledge_base/LPDDR | 1 |
| 04_knowledge_base/HBM | 1 |
| 04_knowledge_base/Large language model | 1 |
| 04_knowledge_base/INT16 | 1 |
| 04_knowledge_base/GPT-3 | 1 |
| 04_knowledge_base/GPU | 1 |
| 04_knowledge_base/TOPS | 1 |
| 04_knowledge_base/MXFP6 | 1 |
| 04_knowledge_base/NF4 | 1 |
| 04_knowledge_base/MSFP | 1 |
| 04_knowledge_base/TFLOPS | 1 |
| 04_knowledge_base/MXFP8 | 1 |
| 04_knowledge_base/MSFP12 | 1 |
| 04_knowledge_base/5nm | 1 |
| 04_knowledge_base/TPU | 1 |
| 04_knowledge_base/Fused Multiply-Add | 1 |
| 04_knowledge_base/DDR | 1 |
| 04_knowledge_base/28nm | 1 |