Skip to content

veloGB10 v0.5.0

Choose a tag to compare

View all tags
@sf-stav sf-stav released this 25 Aug 15:35
v0.5.0
8924240

veloGB10 v0.5.0 — Vision support

Vision. Image input is supported end-to-end on a GPU vision tower (gpu_vision kernels), with
PNG/JPEG/WebP/GIF decoding and a --vision-cpu escape hatch to the CPU reference path. The release
now ships the gpu_vision.ptx kernel artifact alongside the existing PTX set.

Better tool-call support. A single canonical serializer now handles streaming and non-streaming
tool-call output identically, repairs malformed tool-call tags, and no longer drops or leaks text
around tool-call boundaries. New tool-call compliance and serializer test suites.

Prefill / TTFT optimizations. New opt-in prefill levers (tensor-core flash-attention prefill,
v2 W4A4 prefill GEMM, GDN tensor-core chunked scan), all env-gated default off, so the default
serving path is unchanged. Minor bug fixes and optimizations.

Model-id fix. /v1/models and responses now report the model card's base_model instead of a local
directory fragment. --model-name still overrides.

See CHANGELOG.md for the full release history.

Source: dev repo @ 9b60021. Built from the public tree (self-contained), binary sha256
6d6aa435704d2843aa6340036da868c7abe4481c825dde16b43c344a66f2a8e4.

Downloads

  • velogb10-v0.5.0-gb10-sm121.tar.gz - engine binary + all 15 PTX kernel artifacts (incl. vision) + TP launch scripts
  • SHA256SUMS.txt - checksums
  • PROVENANCE.txt - build provenance
Assets 5
Loading