Skip to content

v0.20.0

Compare
Choose a tag to compare
@barronalex barronalex released this 05 Nov 21:23
· 103 commits to main since this release
726dbd9

Highlights

  • Even faster GEMMs
  • BFS graph optimizations
    • Over 120tks with Mistral 7B!
  • Fast batched QMV/QVM for KV quantized attention benchmarks

Core

  • New Features
    • mx.linalg.eigh and mx.linalg.eigvalsh
    • mx.nn.init.sparse
    • 64bit type support for mx.cumprod, mx.cumsum
  • Performance
    • Faster long column reductions
    • Wired buffer support for large models
    • Better Winograd dispatch condition for convs
    • Faster scatter/gather
    • Faster mx.random.uniform and mx.random.bernoulli
    • Better threadgroup sizes for large arrays
  • Misc
    • Added Python 3.13 to CI
    • C++20 compatibility

Bugfixes

  • Fix command encoder synchronization
  • Fix mx.vmap with gather and constant outputs
  • Fix fused sdpa with differing key and value strides
  • Support mx.array.__format__ with spec
  • Fix multi output array leak
  • Fix RMSNorm weight mismatch error