Cut Cross Entropy

JSON →
library 25.1.1 ·python
verified May 23, 2026

Cut Cross Entropy provides a highly memory-efficient implementation of the linear-cross-entropy loss function, primarily optimized for large language models and high-throughput inference scenarios. It is part of the vLLM project. The current version is 25.1.1, indicating a rapid development cycle, likely following a date-based or frequent release cadence, designed for NVIDIA GPUs.

total hits 34
actors 8 distinct systems
last hit 23h ago human
ByteDance
9
GPTBot
2
Script
2
ChatGPT-User
1
Perplexity-User
1
Humans
3

top countries 🇸🇬 Singapore · 🇩🇪 Germany · 🇫🇷 France · 🇺🇸 United States · 🇨🇦 Canada