Feb 23

1. 10:08

   Multi-stage Docker build: Stage 1 compiles llama-cpp-python once, Stage 2 reuses compiled wheels - NO TIMEOUT! Build time 8-12 minutes first time, then cached.

   Sabithulla
   9d2777a
2. 09:36

   Multi-stage Docker build: Stage 1 compiles llama-cpp-python to wheel, Stage 2 installs pre-built wheel - NO TIMEOUT! Pre-download fast-chat model at build time.

   Sabithulla
   3274ec4
3. 09:30

   Switch to Ollama for zero-compilation deployment - pre-downloads models at startup

   Sabithulla
   64f495c
4. 09:27

   Switch to pre-compiled llama-cpp-python binary wheels - no compilation timeout on HF Spaces

   Sabithulla
   939e78c
5. 09:12

   Revert to llama-cpp-python with storage optimization - only load fast-chat at startup

   Sabithulla
   1454974
6. 08:15

   Switch to ctransformers (pre-built, no compilation!) - faster HF Spaces deploy

   Sabithulla
   cf04577
7. 06:20

   Add build-essential & cmake for llama-cpp-python compilation

   Sabithulla
   e57d268
8. 06:17

   Optimize: use --prefer-binary for wheels on Linux but not committed

   Sabithulla
   639666f
9. 06:08

   Remove llama-cpp-python from requirements - already in base image

   Sabithulla
   9f226af
10. 06:06

    Use pre-built llama-cpp-python Docker image - skip compilation

    Sabithulla
    e975c5c
11. 05:44

    Fix: revert to standard pip install (binary-only broke uvicorn install)

    Sabithulla
    96b77f2
12. 05:43

    Force binary wheels only - skip all compilation for fast HF Spaces build

    Sabithulla
    3323511
13. 05:38

    Optimize Dockerfile: skip expensive llama-cpp-python compilation flags

    Sabithulla
    a9145dc
14. 04:51

    Add FastAPI backend with Docker for HuggingFace Spaces

    Sabithulla
    2a72045