Commit History

Auteur SHA1 Bericht Datum
  AlpinDale 656459fd84 make fp8_e4m3 work on nvidia 6 maanden geleden
  AlpinDale 676322dd62 qwen2_moe: mlp_only_layers 6 maanden geleden
  AlpinDale 50b7c13db0 refactor: attention selector (#552) 6 maanden geleden
  AlpinDale b178ae4b4a chore: generalize linear_method to be quant_method (#540) 6 maanden geleden
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) 7 maanden geleden
  AlpinDale fc80f57967 fix: correct file name for qwen2 moe 8 maanden geleden