llama-cli

Introduced benchmark-only synthetic speculative acceptance options for llama-server and llama-cli. This release also provides various pre-compiled binaries for different operating systems and hardware configurations.

This release introduces Vulkan optimizations for Adreno GPUs and fixes a bug in llama-cli related to long prompts. It also includes the removal of an unused Adreno device and updates to matmul for small pipelines.

This release addresses a crash in the llama-cli when an invalid server base URL is used. It also includes improvements to error handling in the review process.

This release fixes an issue where newline characters were incorrectly stripped in multiline input for llama-cli and includes an internal change replacing '&' with 'string_view'.