llama-model-loader

This release introduces support for the Qwen3.8-Flash-Next (qwen4exp) model, including its GGUF implementation, tensor loading, and decode graph. Several bug fixes related to PLE conv state and context handling are also included.

The llama-model-loader now issues a warning when tensor overrides are used alongside mmap, and it has been updated to use pinned memory for tensor overrides.