docs: split Memory-efficient Inference and GGUF+SageAttention into sub READMEs
#19
by gkalstn0 - opened
Move detailed guides to docs/ for better README readability.
docs/memory-efficient-inference.md— CPU offload + FP8 guidedocs/gguf-sageattention.md— GGUF code + SageAttention + benchmark- README section headings and anchors preserved for existing references
- README reduced by ~200 lines
gkalstn0 changed discussion status to closed