Repository navigation

Samsung Exynos AI LiteCore - Enable llama3.2 and gemma3 Models on AOT - #23351

Merged

Jiseong-oh merged 7 commits into

mainfrom

enable-llama-gemma3

Oct 13, 2026

Merged

Samsung Exynos AI LiteCore - Enable llama3.2 and gemma3 Models on AOT#23351
Jiseong-oh merged 7 commits into
mainfrom
enable-llama-gemma3

Commits on Oct 8, 2026
- Support llama3.2 1B in executorch pipeline
  
  Jiseong-oh
  and
  xiongzhan-linghu
  committed
  88e59ec
- Enable weight sharing for LLM
  
  Jiseong-oh
  and
  xiongzhan-linghu
  committed
  d6b5a11
- Support gemma3_1B and llama3.2_1B with float type
  
  Jiseong-oh
  and
  xiongzhan-linghu
  committed
  40279f0
- Update Exynos AI LiteCore Version from v1.2.0 to v1.2.1
  Jiseong-oh
  committed
  288a206
- Change latest SoC for CI
  Jiseong-oh
  committed
  a6fbebb
Commits on Oct 13, 2026
- Merge branch 'main' into enable-llama-gemma3
  Jiseong-oh
  authored
  e71e4b8
- Merge branch 'main' into enable-llama-gemma3
  Jiseong-oh
  authored
  84800e6