Skip to content

v0.4.1
Compare
Choose a tag to compare
@OlivierDehaene OlivierDehaene released this 26 Mar 14:38
· 1272 commits to main since this release
v0.4.1
ab5fd8c
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

Features

  • server: New faster GPTNeoX implementation based on flash attention

Fix

  • server: fix input-length discrepancy between Rust and Python tokenizers
Assets 2
Loading