Content

AI, XR, DevOps, graph theory, knowledge graphs, and digital sovereignty. Deep dives, tutorials, and analysis from across the GraphWiz knowledge base.

All224 AI123 Graphs67 GraphRAG5 Knowledge Graphs6 Visualization1 Algorithms2 Security10 GNN1 LLMs & Graphs2 Agentic AI3

Graphs →AI →

August 19, 2026· ~11 min read

DeepSeek V4 Flash 0731: Initial Experiences on 2x DGX Spark

Practical results from serving DeepSeek's latest MoE mixture-of-experts model on dual DGX Spark systems with vLLM, DSpark speculative decoding, and Anemll optimizations.

deepseekv4-flashmoedgx-spark+5 more

August 18, 2026· ~8 min read

Rust GPU Offload: Portable, Safe, and Fast - Paper Analysis

Deep analysis of arXiv 2608.13759: Rust Offload brings CUDA/HIP-level GPU programming to Rust without vendor lock-in, using LLVM Offload for cross-vendor portability and Rust's type system for memory safety in kernels.

rustgpu

← Previous 1...8 9 10...38 Next →

cuda

hip

+5 more

August 17, 2026· ~4 min read

GRALAN: When Knowledge Graphs Speak LLM Native

GRALAN enables KGs to speak directly in the LLM's semantic space through relational tokens that preserve graph structure. No fine-tuning required — just trainable language mediation.

knowledge-graphsllmgraph-language-modelsrelational-tokens+1 more

August 17, 2026· ~3 min read

X-KGRank: When Small Language Models Lie (And How Knowledge Graphs Fix It)

X-KGRank unifies structural collaborative filtering with LLM-based explanation. A 1.5B parameter model matches a 7B model on explanation quality — but fabricates facts more often when not grounded.

recommendation-systemsknowledge-graphsexplainable-airag+1 more

August 17, 2026· ~5 min read

DyCoder: How Human Developers Think About Code Dependencies

Human developers build partial dependency graphs on-demand — not static global graphs. DyRetriever replicates this pattern, achieving +59.73% Pass@1 on DevEval while being 7.4x faster.

code-generationdependency-graphsragllm+1 more

August 16, 2026· ~4 min read

PGMem: Why Your AI Agent Forgets What It Knows About Users

Persona-memory systems suffer from a validity gap — personas drift without traceable evidence. PGMem solves this with a heterogeneous graph that keeps every signal traceable to its source events.

agentic-aimemory-systemspersonalizationgraphrag+1 more