0.1.6

github-actions released this 24 Jun 00:36

· 229 commits to master since this release

Fix dynamic generator fallback mode (was broken for prompts longer than max_input_len)
Fix inference on ROCm wave64 devices
Made model conversion script part of exllamav2 package
CPU optimizations

Full Changelog: v0.1.5...v0.1.6

Assets 46