A user encountered an issue where LM Studio silently failed to load local LLMs after an automatic runtime update. The error presented as a cryptic, large unsigned exit code, which was identified as a Windows NTSTATUS code. Further investigation in the application logs revealed a CUDA error related to the flash-attention kernel on an RTX 5090 with the Blackwell architecture, indicating a broken fallback path in the updated llama.cpp runtime. AI
IMPACT Local LLM users should disable auto-updates for runtime extension packs to avoid similar model loading failures.
RANK_REASON The item describes a bug and workaround for a specific software tool (LM Studio) that affects local LLM execution, rather than a new model release or significant industry event.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →