Quantization & Low Precision

bfloat16 range vs precision, FP8 and INT8, mixed precision, where dropping precision is safe.

0 / 9 solved
0/9 solved
Question Tags Difficulty Success
1. Same Range, Blurrier Picture
bf16numeric-formats
Medium —
2. Half a Byte, Two Flavors
fp8numeric-formats
Medium —
3. One Ruler vs Many
quantizationcalibration
Medium —
4. Salient Channel Rescue
awqptq +1
Medium —
5. Skinny Weights, Fat Activations
quantizationllm-inference
Hard —
6. Key vs Value Granularity
kv-cache quantizationinference +1
Hard —
7. Second-Order Cleanup
gptqptq +1
Hard —
8. Block-Scaled FP8
fp8quantization +1
Hard —
9. Smooth Before You Round
quantizationgptq +1
Insane —

Up next

9 of 9 questions here are still unsolved.