Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Use python:3.10-slim + compile llama-cpp 0.2.90 (proven working version)"

Full revert to original working configuration"

Use python:3.11-slim + compile llama-cpp with OpenBLAS for CPU speed"

Revert to working config: Q8_0 (was working before), pre-download for fast startup"

Switch to ghcr.io/abetlen/llama-cpp-python (has CPU optimizations) + Q4_K_M + pre-download

Revert to Llama-3.2-1B Q4_K_M (proven working, no thinking issues) with speed optimizations"

Speed overhaul: Qwen3-0.6B Q4_K_M (397MB, 3x faster), pre-built wheel, optimized config

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Create Dockerfile