Michael.Kappel 

Stable public .NET interfaces, records, DTOs, and capability flags for TinyRustLM .slm validation, p2pLLM runtime harness operations, p2pRuntime P2P model sharing, MiniModel manifest metadata, and UAIX.org .uai... More information

Public TinyRustLM .NET SDK for .slm validation, safe model inspection and loading, p2pLLM.com runtime harness lifecycle operations, generation, step/reset, diagnostics, SDK version and capability queries, and... More information

Tensor descriptors, memory descriptors, layouts, and quantization metadata for pure C# local LLM runtime packages.

Stable public interfaces, canonical inference contracts, runtime settings, and diagnostics for pure C# local LLM runtime packages.

Scalar, Vector<T>, and intrinsic-ready CPU kernels for pure C# local LLM runtime inference.

GGUF parser, metadata model, tensor catalog, sharding, and validation for pure C# local LLM runtime packages.

Samplers and logits processors for pure C# local LLM runtime generation.

Controlled local-feed TinyRustLM .NET wrapper for p2pLLM.com .slm conversion command workflows and packaged tinyrustlm-slm-pack tool discovery. This package backs the UAIX.Browser.p2pLLM.Conversion local feed... More information

Public TinyRustLM .NET SDK for p2pRuntime.com peer-to-peer .slm model sharing and import workflows: MiniModel manifest inspection, local piece verification, signed-manifest verification, share-kit metadata,... More information

Portable acceleration backend contracts, registry, device probing, selection policies, fallback reporting, and diagnostics for UAIX local LLM runtime packages.

Public TinyRustLM .NET SDK for UAIX.org .uai AI memory packages, AI Memory Package Wizard workflows, discoverable setup catalog, embedded AI digest adoption, point-agent setup URLs, prompt nudges, Safe... More information

Tokenizer implementations and chat template rendering for pure C# local LLM runtime packages.

RID-specific Windows x64 CUDA legacy package slot for Tesla K80 compute capability 3.7 compatibility in UAIX local LLM runtime acceleration.

Local-only managed GGUF LLM runtime facade for LocalEndpoint desktop integration.

LLaMA-family graph configuration and reference forward-pass primitives for pure C# local LLM runtime inference.

RID-specific Windows x64 CUDA native asset package slot for UAIX local LLM runtime acceleration.

Shared interfaces and memory entry models for UAIX UAI-1 .NET clients, AI memory stores, project handoff integrations, and persona-aware package flows.

ROCm backend capability reporting, AMD GPU diagnostics, and explicit selection surface for UAIX local LLM runtime acceleration.

Managed CPU reference backend registration, capability reporting, and diagnostics for UAIX local LLM runtime acceleration selection.

DirectML backend capability reporting, Windows compatibility diagnostics, and explicit selection surface for UAIX local LLM runtime acceleration.