Autor: t0mi

How I extended the SenseCAP Indicator D1S with additional sensors and MariaDB integration with 100% AI-generated code Introduction Air quality monitoring has become increasingly important, whether for home environments, offices, or industrial applications. When I discovered the SenseCAP Indicator D1S by Seeed Studio, I saw an excellent foundation for a comprehensive environmental monitoring station. However,

Squeezing Maximum Performance from a 355B MoE Model – A Practical Benchmark Guide Introduction GLM-4.7 is an impressive open-source MoE (Mixture of Experts) model with 400 billion parameters that can run on consumer hardware thanks to its architecture. In this comprehensive benchmark, I’ll show how I achieved 619 tokens per second for prompt processing and

Hardware Overview Inference Engine Compilation First Attempts with BF16 Quantization Early Q8_0 Tests (Pre-BIOS Optimization) BIOS Optimization and BLAS Experiments Batch Size Sweep (with optimal 64 threads) Testing Experimental Flags (Graph Reuse & RoPE) Final Linux Tweaks (THP, Cache Drop, BLAS Threading) Final Optimized Setup Some Real-World Benchmarks Lockstep vs Independent Memory Mode NEW: Further