Skip to content

BaseRT engine 0.1.6

Choose a tag to compare

View all tags
@prabod prabod released this 18 Jul 07:10
v0.1.6
67c2dac
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

BaseRT 0.1.6

  • Qwen 3.5 / 3.6 support: dense, MoE, and vision-language models (hybrid Gated-DeltaNet architecture), in both the runtime and basert convert.
  • M5 tensor-core kernels included: release binaries now ship the Metal 4 kernel library (baseRT_tensor.metallib) — earlier releases were missing it, so M5 GPUs fell back to slower kernels. Loads automatically; older Macs are unaffected.
  • Big-model support: models larger than the GPU wiring limit now load and decode at full speed (e.g. a 28 GB model on a 48 GB Mac) instead of failing.
  • Qwen3.5-VL accuracy: image preprocessing and multimodal RoPE now match the reference implementation token-for-token.
  • CLI: basert-complete accepts -n for max tokens; unknown flags are now errors.
  • Requires macOS 15+ (Metal 4 kernels engage on macOS 26 / M5).

Contents: libbaseRT.dylib (embedded kernels) + basert CLI + basert-* runtime tools + headers.

Assets 4
Loading