Skip to content

v0.44.0

Choose a tag to compare

View all tags
@michaelneale michaelneale released this 24 Mar 09:30
· 1900 commits to main since this release
v0.44.0
60e0028

Rebased llama.cpp fork on latest upstream (419 commits).

Upstream highlights picked up:

  • RPC remote code execution security patch
  • Metal CONV_3D support
  • bf16 native flash attention (CUDA)
  • Server Host header fix, httplib dynamic threads
  • Grammar parsing fix (stack overflow prevention)
  • Memory fix for recurrent models

Our patches (all rebased clean):

  • Zero-transfer tensor loading (SET_TENSOR_GGUF)
  • RPC probing skip
  • get_alloc_size cache
  • B2B direct server-to-server transfers
  • MoE expert routing + analysis/split tools

Also: removed stale PLAN.md

Assets 3
Loading