Repository navigation

feat(gguf): serve GLM-5.3-Flash GGUF checkpoints on glm5-next - #721

Merged

jason-fxz merged 7 commits into

FlashML-org:mainfrom

void-mckenzie:feat/gguf-glm5-next

Oct 20, 2026

Merged

feat(gguf): serve GLM-5.3-Flash GGUF checkpoints on glm5-next#721
jason-fxz merged 7 commits into
FlashML-org:mainfrom
void-mckenzie:feat/gguf-glm5-next

Commits on Oct 20, 2026
- feat(gguf): serve GLM-5.3-Flash GGUF checkpoints on glm5-next
  
  mukmckenzie
  authored and
  void-mckenzie
  committed
  a02b04d
- fix(gguf): refuse unread scale tensors in glm5-next ggufs
  void-mckenzie
  committed
  e08af5a
- fix(gguf): serve the quantized tensors of unsloth dynamic glm5-next quants
  void-mckenzie
  committed
  b0ee0d2
- fix(gguf): treat the glm5 pre-tokenizer spelling like glm4
  void-mckenzie
  committed
  137697e
- fix(gguf): size the mmq tail padding by ggml type and k
  void-mckenzie
  committed
  1848989
- fix(gguf): take the older glm5-next writer variants in stride
  void-mckenzie
  committed
  1d61f12
- fix(gguf): glm5-next review cleanups
  void-mckenzie
  committed
  b9e4849