What's Changed
- ci: avoid unbounded parallelism by @dhiltgen in #16966
- fix cuda toolkit lookup and parallel by @MarkWard0110 in #16613
- docs(cloud): update retirement list by @mxyng in #17000
- discover: fall back to standard CUDA when the JetPack runner is absent by @kevinpark1217 in #16949
- agent: harness core by @ParthSareen in #16963
- llama: clean up dead code from llama-server work by @dhiltgen in #17007
- rocm: remove no longer supported devices by @dhiltgen in #17010
- compat: use UTF-8-safe file open by @dhiltgen in #16999
- llama: enable FA on CUDA CC 6.x GPUs by @dhiltgen in #16994
- mlx: x/create rewrite by @pdevine in #16919
- llama.cpp update by @dhiltgen in #17055
- server: remove OLLAMA_EXPERIMENT=client2 by @mxyng in #16962
- mlx: update to de7b4ed9 by @dhiltgen in #17056
New Contributors
- @kevinpark1217 made their first contribution in #16949
Full Changelog: v0.31.1...v0.31.2-rc0