Skip to content

v0.1.2

Compare
Choose a tag to compare
@UnicornChan UnicornChan released this 15 Aug 17:39
· 389 commits to main since this release
77a34c2
  1. Support windows native. #4
  2. Support multiple GPU. #8
  3. Support llamfile as linear backend.
  4. Support new model: mixtral 8 * 7B and 8 * 22B
  5. Support q2k, q3k, q5k dequant on gpu. #16
  6. Support github action to create pre compile package
  7. Support shared memory in different operator
  8. Fix some bugs on build from source #23