Major Changes

• Grammar Resampling by @martindevans, @m0nsky & @phil-scott-78 in https://github.com/SciSharp/LLamaSharp/pull/1109
• Added 'strict' parameter for template retrieval by @Lyrcaxis in https://github.com/SciSharp/LLamaSharp/pull/1124
• March 2025 version update by @martindevans in https://github.com/SciSharp/LLamaSharp/pull/1126

Bug Fixes

• Various fixes regarding special tokens (embeddings & anti-prompt) by @Lyrcaxis in https://github.com/SciSharp/LLamaSharp/pull/1112
• Fix Kernel Memory by @martindevans in https://github.com/SciSharp/LLamaSharp/pull/1081
• Updates json gbnf to match llama.cpp example by @phil-scott-78 in https://github.com/SciSharp/LLamaSharp/pull/1098
• InteractiveExecutor now stops at EOS tokens again by @dpmm99 in https://github.com/SciSharp/LLamaSharp/pull/1092

Other Changes

• Update README.md by @sangyuxiaowu in https://github.com/SciSharp/LLamaSharp/pull/1086
• Smaller Unit Test Model by @martindevans in https://github.com/SciSharp/LLamaSharp/pull/1105
• Update Microsoft.Extensions.AI to 9.3.0-preview.1.25114.11 by @stephentoub in https://github.com/SciSharp/LLamaSharp/pull/1102
• Cleaned up non-important warnings from the error list by @Lyrcaxis in https://github.com/SciSharp/LLamaSharp/pull/1111
• Update to M.E.AI 9.3.0-preview.1.25161.3 by @stephentoub in https://github.com/SciSharp/LLamaSharp/pull/1127
• Improved Memory Rental by @martindevans in https://github.com/SciSharp/LLamaSharp/pull/1113

Full Changelog: https://github.com/SciSharp/LLamaSharp/compare/v0.21.0...v0.22.0