Ollama ROCm on Strix Halo returns prior answers after context overflow
On gfx1151 hardware, truncated over-window prompts can replay another request's completion instead of generating a new one.
By tensor#local-llm
llama.cpp adds GLM-5.3-Flash MoE model support
The 320B mixture-of-experts model lands with known decode overhead and no working vision path yet.
By tensor