Repository navigation

Mtp/qwen4exp nextn - #59

Merged

InfernalDread merged 6 commits into

InfernalDread:qwen_38_flash_unsloth_mtpfrom

unslothai:mtp/qwen4exp-nextn

Sep 2, 2026

Commits on Sep 2, 2026
- gguf-py : register the qwen4exp NextN tensors
  
  ryanmonsurate
  authored and
  danielhanchen
  committed
  518efa2
- model : add the qwen4exp NextN/MTP draft head
  
  ryanmonsurate
  authored and
  danielhanchen
  committed
  e52b4b0
- convert : export the qwen4exp NextN/MTP draft head
  
  ryanmonsurate
  authored and
  danielhanchen
  committed
  2b984b9
- llama: let an MTP draft borrow the target's embeddings and lm head
  danielhanchen
  committed
  78ede59
- qwen4exp: allow loading a draft-only MTP export
  danielhanchen
  committed
  b0653f3
- ggml-cuda: key the CUDA graph cache by shape
  danielhanchen
  committed
  5a08a71