Posts tagged #llm

12 posts tagged 'llm'.

• R9700 Backup GPU Total Failure - Getting the Cause Wrong Twice
• R9700 Backup GPU - Wiring Self-Healing In and Rechecking the Concurrency Bump
• R9700 Backup GPU - Bottleneck Root Cause and a Dead-Slot Detector
• Qwen3.6-35B-A3B on an AMD R9700 with llama.cpp: Vulkan vs HIP, Concurrent Slots, and MTP Measured in tokens/s
• Qwen3.8-27B on a Single RTX 5090 with vLLM: NVFP4 + MTP Tuning Results and the KV Cache Bottleneck
• I Finally Changed the Temperature for Real - and Overrode a Pre-Registered Rule That Said "Reject"
• Checking the AI Judgment Models' Sampling Settings — Wrong Values All Along
• Switching to a New Local Model, and Quietly Keeping the Old One Around
• Local LLM Speed by GPU Generation, and Our Production's Daily Token Volume
• Watching AI Be Confidently Wrong
• One Leg of the Ensemble Had Been Running on Zero Evidence for Six Months
• Hidden Failure Patterns Found While Comparing Three Local LLMs