Nov 7 2 days ago

1. 14:36

   Update app.py Running

   Mohd-Shujath
   Verified signature

   3f0f6fc
2. 14:05

   Update app.py

   Mohd-Shujath
   Verified signature

   01aaebd
3. 13:56

   fixing

   Mohd-Shujath
   316f370
4. 13:54

   Use uvicorn with environment PORT

   Mohd-Shujath
   fb2297e
5. 13:52

   fixed

   Mohd-Shujath
   2419d6a
6. 13:05

   Add spaces.GPU decorator for ZeroGPU support

   Mohd-Shujath
   2c0a1bd
7. 12:58

   Add uvicorn server startup on port 7860

   Mohd-Shujath
   5ec38d4
8. 12:56

   Fix version sort + add GGUF file validation

   Mohd-Shujath
   4fb13be
9. 12:51

   Fix: use +cpu tagged manylinux wheel from AIencoder (no CUDA deps)

   Mohd-Shujath
   2d7b7d3
10. 12:43

    Auto-bootstrap precompiled manylinux llama-cpp-python

    Mohd-Shujath
    56e59a7
11. 12:32

    Switch to ctransformers for pure glibc compatibility

    Mohd-Shujath
    c8ce4c2
12. 12:28

    Add musl package for llama-cpp runtime

    Mohd-Shujath
    18ec402
13. 12:24

    Updated llama-cpp-python

    Mohd-Shujath
    029fad0
14. 12:21

    Use ctransformers

    Mohd-Shujath
    2872a72
15. 12:17

    Use prebuilt wheels for llama-cpp-python

    Mohd-Shujath
    2c44df6
16. 11:39

    Deploy fine-tuned driver

    Mohd-Shujath
    176cf9b
17. 11:32

    initial commit

    Mohd-Shujath
    Verified signature

    2eac1e6