0.1.50

Llama 3 working at 100+ tokens per second in simple

What's Changed

• Bumped version to 0.1.50 by @github-actions in #253
• Bump cc from 1.0.91 to 1.0.94 by @dependabot in #257
• Bump rustls from 0.21.6 to 0.21.11 by @dependabot in #265
• Bump docker/setup-buildx-action from 3.2.0 to 3.3.0 by @dependabot in #259
• Updated llama-cpp (bot) by @MarcusDunn in #267

Full Changelog: 0.1.49...0.1.50