[dependabot]

Updated LLamaSharp from 0.27.0 to 0.30.0.

Release notes

Sourced from LLamaSharp's releases.

0.30.0

Major Changes

• feat(cuda): add CUDA 13.0.0 jobs to the compile workflow by @​modelpath-dev in feat(cuda): add CUDA 13.0.0 jobs to the compile workflow SciSharp/LLamaSharp#1439
• feat(cuda): probe cuda13 native libraries before cuda12 by @​modelpath-dev in feat(cuda): probe cuda13 native libraries before cuda12 SciSharp/LLamaSharp#1440
• feat(cuda): add LLamaSharp.Backend.Cuda13 packages by @​modelpath-dev in feat(cuda): add LLamaSharp.Backend.Cuda13 packages SciSharp/LLamaSharp#1441
• Add Microsoft Agent Framework (Microsoft.Agents.AI) with RAG Example by @​zsogitbe in Add Microsoft Agent Framework (Microsoft.Agents.AI) with RAG Example SciSharp/LLamaSharp#1423
• Expose llama_model_params.devices as IModelParams.Devices by @​ipevo-brooks in Expose llama_model_params.devices as IModelParams.Devices SciSharp/LLamaSharp#1447

Bug Fixes

• Detect Vulkan via the loader before falling back to vulkaninfo by @​ipevo-brooks in Detect Vulkan via the loader before falling back to vulkaninfo SciSharp/LLamaSharp#1446
• Remove SemanticKernel and KernelMemory leftovers by @​m0nsky in Remove SemanticKernel and KernelMemory leftovers SciSharp/LLamaSharp#1426
• Disable SSE4.2 in noavx native builds by @​modelpath-dev in Disable SSE4.2 in noavx native builds SciSharp/LLamaSharp#1438
• Fix RawRepresentationFactory settings being overwritten in AsChatClient by @​Laurianti in Fix RawRepresentationFactory settings being overwritten in AsChatClient SciSharp/LLamaSharp#1442
• Fixed CI by @​martindevans in Fixed CI SciSharp/LLamaSharp#1458

Other Changes

• Read the release version from LLamaSharp.csproj by @​m0nsky in Read the release version from LLamaSharp.csproj SciSharp/LLamaSharp#1427
• Merge the minor and patch release workflows into one by @​m0nsky in Merge the minor and patch release workflows into one SciSharp/LLamaSharp#1430
• Push the API references with GITHUB_TOKEN, falling back to a pull request by @​Laurianti in Push the API references with GITHUB_TOKEN, falling back to a pull request SciSharp/LLamaSharp#1453
• Fix the API references workflow for XMLDoc2Markdown 6 by @​Laurianti in Fix the API references workflow for XMLDoc2Markdown 6 SciSharp/LLamaSharp#1443
• Build the API references from net10.0 by @​Laurianti in Build the API references from net10.0 SciSharp/LLamaSharp#1462
• Fixed release-trigger.yml by @​martindevans in Fixed release-trigger.yml SciSharp/LLamaSharp#1464
• Big package update by @​martindevans in Big package update SciSharp/LLamaSharp#1457
• Cleanup Unused Things by @​martindevans in Cleanup Unused Things SciSharp/LLamaSharp#1459

New Contributors

• @​modelpath-dev made their first contribution in Disable SSE4.2 in noavx native builds SciSharp/LLamaSharp#1438
• @​Laurianti made their first contribution in Fix RawRepresentationFactory settings being overwritten in AsChatClient SciSharp/LLamaSharp#1442
• @​ipevo-brooks made their first contribution in Detect Vulkan via the loader before falling back to vulkaninfo SciSharp/LLamaSharp#1446

Full Changelog: SciSharp/LLamaSharp@v0.29.0...v0.30.0

0.29.0

Major Changes

• Updated to llama.cpp 815a2a5915f22ce6a760c676389c5dfe8535c08f (b10221) by @​martindevans in Updated to llama.cpp 815a2a5915f22ce6a760c676389c5dfe8535c08f (b10221) SciSharp/LLamaSharp#1414

Bug Fixes

• Implement Sequence ID pooling in BatchedExecutor to prevent native SeqMax overflow and crashes by @​zsogitbe in Implement Sequence ID pooling in BatchedExecutor to prevent native SeqMax overflow and crashes SciSharp/LLamaSharp#1386
• Disable GGML_F16C GGML_BMI2 for noavx buid (Fixes #​1407) by @​butameron in Disable GGML_F16C GGML_BMI2 for noavx buid (Fixes #1407) SciSharp/LLamaSharp#1408
• Allow arbitrary ChatSession message interleaving by @​YoMosa2009 in Allow arbitrary ChatSession message interleaving SciSharp/LLamaSharp#1417
• Fix null DryRun output by @​martindevans in Fix null DryRun output SciSharp/LLamaSharp#1419

Other Changes

• Remove LLama.Experimental by @​martindevans in Remove LLama.Experimental SciSharp/LLamaSharp#1421
• Remove SemanticKernel and KernelMemory by @​martindevans in Remove SemanticKernel and KernelMemory SciSharp/LLamaSharp#1420

New Contributors

• @​butameron made their first contribution in Disable GGML_F16C GGML_BMI2 for noavx buid (Fixes #1407) SciSharp/LLamaSharp#1408
• @​YoMosa2009 made their first contribution in Allow arbitrary ChatSession message interleaving SciSharp/LLamaSharp#1417

Full Changelog: SciSharp/LLamaSharp@v0.27.0...v0.29.0

Commits viewable in compare view.