Commit History

Author SHA1 Message Date
  AlpinDale 7c825e50be fix: correct FP8 support check on Ada+ GPUs by using compressed-tensors (#1110) 6 days ago
  AlpinDale 201db10f02 models: add support for Phi3 MoE 1 month ago
  AlpinDale 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) 1 month ago