Commit History

  1. Report throughput in consistent units⁠

    b582a21
  2. Correct the latency claim: measure against llama.cpp, not our own worst case⁠

    82bf4d8
  3. Correct README to the verified claims⁠

    65d070e

  1. Filter empty thoughts from recording and chat display

    Verified signature
    e431d79
  2. Collapse empty chat-log black box; chat column hugs text bar

    Verified signature
    cdea7ed
  3. Full-vocab HVM cache (128K tokens) via chunked bf16 projection

    Verified signature
    f7a2fac
  4. Thought recording + contemplate mode + denoise parser for int8 digit collapse

    Verified signature
    3f49d51
  5. fix: chat messages persist + agent generates 256 tokens per round (was 32)

    Verified signature
    cf620e1
  6. Trim test target to Space-shipping files (C libs + py_compile only)

    Verified signature
    6cce3a6
  7. Drop __pycache__, clean slate

    Verified signature
    9e19cd4
  8. Port full dashboard engine: phoenix_dashboard + agent_core + hyper_vocab_memory + bqsm_assist

    Verified signature
    bdf5f4a

  1. Add chat debug logging

    Nicholas Bumgarner
    c1298e1
  2. Force rebuild

    Nicholas Bumgarner
    92af58e
  3. Increase chat timeout to 120s for Space CPU

    Nicholas Bumgarner
    933ff98
  4. Init ring buffers in start_mixer

    Nicholas Bumgarner
    a570df2
  5. Support both phoenix and mixer engines in chat

    Nicholas Bumgarner
    8f7952f
  6. Update mixer.c with LM head projection + ring buffer chat I/O

    Nicholas Bumgarner
    b918c0d
  7. Update mixer.c with actual ternary weight decoding from model

    Nicholas Bumgarner
    2ebca3e
  8. Add mixer.c source to Space repo

    Nicholas Bumgarner
    18881f2
  9. Add Start Mixer button + start_mixer function for fast mixing ring engine

    Nicholas Bumgarner
    cdad13a
  10. Revert to ring buffer protocol; optimize log tail reading

    Nicholas Bumgarner
    b356ed7
  11. Fix chat protocol: use named pipe (/tmp/phoenix_chat.pipe) per phoenix_brain.c chat mode

    Nicholas Bumgarner
    76b2b96
  12. Download binary + model to /tmp to avoid Space auto-restart

    Nicholas Bumgarner
    ec34b87
  13. Cache binary download (no force_download); fix indentation

    Nicholas Bumgarner
    3aec1bb
  14. Fix stop_phoenix: minimize lock holding, close fds outside lock

    Nicholas Bumgarner
    a53b1da
  15. Add phoenix daemon monitor thread + tick log display

    Nicholas Bumgarner
    488f97e
  16. Force re-download binary; fix lock contention in get_boot_status

    Nicholas Bumgarner
    faa1f0b
  17. Fix lock contention: get_boot_status reads without lock, phox_chat checks minimal

    Nicholas Bumgarner
    3e5b14e
  18. Download pre-built phoenix binary from HF Hub instead of compiling on Space

    Nicholas Bumgarner
    adcbc7e
  19. Pre-built static phoenix binary; skip compilation on boot

    Nicholas Bumgarner
    d0f24f6
  20. Manual boot: tokenizer loads at startup, full boot on button click. Non-blocking stop_phoenix.

    Nicholas Bumgarner
    4eb0c7c
  21. Remove blocking wait loop; tick() checks daemon log instead

    Nicholas Bumgarner
    9317c1d
  22. Non-blocking boot wait: 0.5s sleep, only last 20 log lines

    Nicholas Bumgarner
    fdff78d
  23. Fix boot wait loop: release lock between checks, extended timeout

    Nicholas Bumgarner
    e73f64f
  24. Touch app.py to force Space rebuild

    Nicholas Bumgarner
    6f7f402
  25. Fix tokenizer get_vocab API call

    Nicholas Bumgarner
    0ace216
  26. Fix Gradio 6.22 + remove torch dep: use tokenizers lib, gr.Timer API

    Nicholas Bumgarner
    4aa8326
  27. Fix Gradio 6.0 compat: remove css/interactive params, fix tokenizer loading

    Nicholas Bumgarner
    26b395e
  28. Fix short_description length

    Nicholas Bumgarner
    fb8c492
  29. Convert to Gradio: Phox wave-rider inference engine⁠

    Nicholas Bumgarner
    a2124e2

  1. initial commit

    Verified signature
    850c7dc