Scaling FP8 training to trillion-token LLMs

Maxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry · 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

cs.LG · 2026-05-19 · 2 refs

citing papers explorer

Showing 1 of 1 citing paper.

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cs.LG · 2026-05-19 · unreviewed · ref 15 · 2 links