Fix CPU thread oversubscription: cap n_threads to 2 (cpu-basic vCPUs) for faster generation

Re-deploy llama.cpp + GGUF CPU serving (default Q4_K_M); fast CPU inference

Revert "Migrate CPU serving to llama.cpp + Q5_K_M GGUF (was bf16 transformers)"

Revert "Make torch/transformers/peft lazy imports so CPU Space boots without them"

Make torch/transformers/peft lazy imports so CPU Space boots without them

Migrate CPU serving to llama.cpp + Q5_K_M GGUF (was bf16 transformers)

Fix bugs

Fix bugs

Update CPU warning banner with accurate load and query times

Fix inference device bug, auto-load model, remove fine-tuning console, UI cleanup

initial deployment