0.0.12

github-actions released this 01 Nov 17:27

· 41 commits to master since this release

e384d39

Support MiniMaxM2ForCausalLM
Graphs (reduce CPU overhead)
Misc. optimizations
Allow loading FP8 tensors (for quantization only, converted to FP16 on-the-fly)
Fix some bugs

Full Changelog: v0.0.11...v0.0.12

Assets 19