Nov 13 2 days ago

1. 16:08

   Fix tokenizer startup: use saved fast tokenizer and compatible protobuf runtime

   SEE7
   Verified signature

   88a2f11
2. 16:07

   Pin translation Space to trained and tested AstheralTranslate release f9e5dcb2581f10f4646c5d9cf83836723adf08f5

   SEE7
   Verified signature

   ec13a65
3. 15:51

   Build five-language translation UI and actual ZeroGPU inference runtime

   SEE7
   Verified signature

   2bc6811
4. 15:31

   Preserve ZeroGPU platform errors using session queue events instead of null call errors

   SEE7
   Verified signature

   8be89d0
5. 15:29

   Expose sanitized quota readiness and preserve precise budget errors before queue

   SEE7
   Verified signature

   a06dbd3
6. 15:19

   Remove public account/model headers and visitor OAuth checks; keep server quota guard with retries

   SEE7
   Verified signature

   ffd5312
7. 15:10

   Add coding workspace, text/code references, per-model profiles and Continue reply

   SEE7
   Verified signature

   4b43fe7
8. 05:17

   Allow 4096-token replies and 110-second generation with 180-second quota reserve

   SEE7
   Verified signature

   7244dd9
9. 04:57

   Pin Astheral chat to tested V3 weights; preserve UI and quota guard

   SEE7
   Verified signature

   92a2cd2
10. 03:49

    Keep selected GGUF identity in responses and reset missing temporary models

    SEE7
    Verified signature

    0786d8f
11. 03:47

    Register the GGUF ZeroGPU handler during application startup

    SEE7
    Verified signature

    9c78f5e
12. 03:46

    Add private GGUF upload, model selection and quota-guarded CUDA inference

    SEE7
    Verified signature

    b66be8b
13. 03:38

    Serve llama-ui routes directly without Gradio SSR interception

    SEE7
    Verified signature

    766c469
14. 03:36

    Preserve Hugging Face visitor headers through the Gradio bridge

    SEE7
    Verified signature

    e2cae95
15. 03:34

    Install real llama-ui with streaming Astheral ZeroGPU adapter and existing quota guard

    SEE7
    Verified signature

    66474d0
16. 03:22

    Pause GPU generation before final three minutes of included quota

    SEE7
    Verified signature

    8ff525a
17. 03:15

    Correct Gradio examples for response settings inputs

    SEE7
    Verified signature

    94f80ad
18. 03:13

    Deploy private Astheral demo with real weights on ZeroGPU

    SEE7
    Verified signature

    0339afd
19. 03:11

    initial commit

    SEE7
    Verified signature

    7312ec4