Ollama v0.40.8-rc0 发布：新增对 Flint 模型的支持

v0.40.8-rc0: mlx: add Flint model support (#19181)

要点速览

Ollama v0.40.8-rc0 发布，新增对 Flint 模型的支持，通过保留源工具 JSON 和解码 API 值使 Flint 能在提示中维持数值类型和模式顺序，同时保持现有 API 序列化不变。

正文

Preserve source tool JSON alongside decoded API values so Flint can retain
numeric types and schema order in prompts. Existing API marshaling is unchanged.

Assemble ModelOpt expert banks during safetensors import, and reject direct
Flint NVFP4 creation before conversion. Other models retain their existing
import and quantization paths.

Add optional learned sinks and device causal masks to shared MLX attention.
Existing callers retain the no-sink and host-mask paths; Flint opts into the
new behavior.