Hugging Face's logo

Spaces:
Leon4gr45
/
phi_inference
Paused

App Files Community
phi_inference

Commit History

  1. Document split KV quant + cache-reuse env vars

    Leon4gr45
    Verified signature
    abde511

  2. Split K/V cache quant, 16K ctx, cache-reuse, generation smoke test

    Leon4gr45
    Verified signature
    4548f4e

  1. safety: cap threads at CPU_THREADS_MAX (default 2) to prevent oversubscription if detection over-reports

    Leon4gr45
    Verified signature
    911ccc5

  2. feat: cgroup-aware vCPU auto-detection (respects container CPU limit; no CPU_THREADS env needed)

    Leon4gr45
    Verified signature
    eb5a9f7

  3. Delete list_models.py with huggingface_hub

    Leon4gr45
    Verified signature
    2073253

  4. Delete download_model.py with huggingface_hub

    Leon4gr45
    Verified signature
    3bbdc74

  5. port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary

    Leon4gr45
    Verified signature
    4baaa2f

  1. Update Dockerfile

    Leon4gr45
    Verified signature
    0add691

  2. Update app.py

    Leon4gr45
    Verified signature
    1aecc68

  3. Update app.py

    Leon4gr45
    Verified signature
    2a7a917

  4. Update app.py

    Leon4gr45
    Verified signature
    6947e38

  5. Update app.py

    Leon4gr45
    Verified signature
    dcfb6cb

  6. Update app.py

    Leon4gr45
    Verified signature
    8b44be5

  7. Update Dockerfile

    Leon4gr45
    Verified signature
    7e2c73d

  8. Create download_model.py

    Leon4gr45
    Verified signature
    302a3ec

  9. Upload folder using huggingface_hub

    Leon4gr45
    Verified signature
    f3a62ee

  10. Upload folder using huggingface_hub

    Leon4gr45
    Verified signature
    36fcbf8

  11. initial commit

    Leon4gr45
    Verified signature
    8c345e4