0.50.1: RTX Spark Support
This release adds support for additional hardware platforms and improves performance on RTX Spark / DGX Spark.
Highlights
- Support added for NVIDIA RTX Spark products running Windows on ARM64 (#2038, #2037, #2032)
- Improved 4bit GEMM dispatch heuristics for NVIDIA GB10 (#2030)
- Support for AMD CDNA5 hardware (e.g. MI455X)
What's Changed
- Add ROCm CDNA5 (gfx1250) support by @zjin-lcf in #2023
- chore(deps): bump the actions group with 3 updates by @dependabot[bot] in #2022
- Update README by @matthewdouglas in #2024
- Fix truncated FP4 constant in Triton dequantize_fp4_tree by @Anai-Guo in #2026
- docs: add installation instructions for NVIDIA Spark (ARM64) devices by @mfuntowicz in #2037
- fix: missing compilation flag on recent msvc version by @mfuntowicz in #2032
- build: Add Windows ARM64 build with CUDA 13.4 for RTX Spark by @matthewdouglas in #2038
- Add sm121 (GB10) tier to the 4-bit GEMM dispatch heuristic
by @yashb98 in #2030
New Contributors
- @zjin-lcf made their first contribution in #2023
- @Anai-Guo made their first contribution in #2026
- @yashb98 made their first contribution in #2030
Full Changelog: 0.50.0...0.50.1