Ollama releases· pdevine·· 7 天前12
Ollama v0.40.16-rc0 发布：为 MLX 运行器添加涟漪预览支持
v0.40.16-rc0: Add ripple preview support to the MLX runner (#19592)
要点速览
Ollama v0.40.16-rc0 发布，为 MLX 运行器新增涟漪预览支持；修复 Claude Code 路由和模型错误。
正文
What's Changed
- openai: forward truncation option in responses requests by @marlonferreira1800-hue in #19501
- openai: return an empty array for /v1/models when no models are installed by @liangliang205 in #19539
- llama.cpp: version bump b12177 by @dhiltgen in #19576
- README: add Quock to Mobile community integrations by @matteocelani in #19361
- windows: add CUDA 13.5 and SM 103 for ARM64 by @dhiltgen in #19580
- MLX: make Qwen3.8 Flash Next memory efficient by @dhiltgen in #18078
- launch: fix Claude Code routing and retired model errors by @hoyyeva in #19587
- Add ripple preview support to the MLX runner by @pdevine in #19592
New Contributors
- @marlonferreira1800-hue made their first contribution in #19501
- @liangliang205 made their first contribution in #19539
Full Changelog: v0.40.15...v0.40.16-rc0
来源: Ollama releases · github.com