v0.4.1
版本发布时间: 2023-03-26 22:38:21
huggingface/text-generation-inference最新发布版本:v3.0.1(2024-12-12 04:13:58)
Features
- server: New faster GPTNeoX implementation based on flash attention
Fix
- server: fix input-length discrepancy between Rust and Python tokenizers