FP8
Type: Concept
As of November 2026, FP8 has been mentioned in one podcast episode on Kaggle (May 2025). A quantization technique used for keeping weights in FP8 to speed up inference.
| Mentioned in | 1 episode on 1 podcast (as of November 2026) |
|---|---|
| First heard | May 2025 on Kaggle |
| Field | Technology |
Who talks about FP8 on podcasts?
FP8 came up; the most recent mention was May 2025 on Kaggle.