kamiwaza-mlx 0.1.5

Unified MLX server & CLI (language and vision) with OpenAI-compatible endpoints

Kamiwaza-MLX 📦

A simple openai (chat.completions) compatible mlx server that:

• Supports both vision models (via flag or model name detection) and text-only models
• Supports streaming boolean flag
• Has a --strip-thinking which will remove tag (in both streaming and not) - good for backwards compat
• Supports usage to the client in openai style
• Prints usage on the server side output
• Appears to deliver reasonably good performance across all paths (streaming/not, vision/not)
• Has a terminal client that works with the server, which also support syntax like image:/Users/matt/path/to/image.png Describe this image in detail

Tested largely with Qwen2.5-VL and Qwen3 models

Note: Not specific to Kamiwaza (that is, you can use on any Mac, Kamiwaza not required)

pip install kamiwaza-mlx

# start the server
a) python -m kamiwaza_mlx.server -m ./path/to/model --port 18000
# or, if you enabled the optional entry-points during install
b) kamiwaza-mlx-server -m ./path/to/model --port 18000

# chat from another terminal
python -m kamiwaza_mlx.infer -p "Say hello"

The remainder of this README documents the original features in more detail.

MLX-LM 🦙 — Drop-in OpenAI-style API for any local MLX model

A FastAPI micro-server (server.py) that speaks the OpenAI /v1/chat/completions dialect, plus a tiny CLI client (infer.py) for quick experiments. Ideal for poking at huge models like Dracarys-72B on an M4-Max/Studio, hacking on prompts, or piping the output straight into other tools that already understand the OpenAI schema.

---

✨ Highlight reel

Feature	Details
🔌 OpenAI compatible	Same request / response JSON (streaming too) – just change the base-URL.
📦 Zero-config	Point at a local folder or HuggingFace repo (-m /path/to/model).
🖼️ Vision-ready	Accepts {"type":"image_url", …} parts & base64 URLs – works with Qwen-VL & friends.
🎥 Video-aware	Auto-extracts N key-frames with ffmpeg and feeds them as images.
🧮 Usage metrics	Prompt / completion tokens + tokens-per-second in every response.
⚙️ CLI playground	infer.py gives you a REPL with reset (Ctrl-N), verbose mode, max-token flag…

---

🚀 Running the server

# minimal
python server.py -m /var/tmp/models/mlx-community/Dracarys2-72B-Instruct-4bit

# custom port / host
python server.py -m ./Qwen2.5-VL-72B-Instruct-6bit --host 0.0.0.0 --port 12345

Default host/port: 0.0.0.0:18000

Most useful flags:

Flag	Default	What it does
-m / --model	mlx-community/Qwen2-VL-2B-Instruct-4bit	Path or HF repo.
--host	0.0.0.0	Network interface to bind to.
--port	18000	TCP port to listen on.
-V / --vision	off	Force vision pipeline; otherwise auto-detect.
--strip-thinking	off	Removes <think>…</think> blocks from model output.
--enable-prefix-caching	True	Enable automatic prompt caching for text-only models. If enabled, the server attempts to load a cache from a model-specific file in --prompt-cache-dir. If not found, it creates one from the first processed prompt and saves it.
--prompt-cache-dir	./.cache/mlx_prompt_caches/	Directory to store/load automatic prompt cache files. Cache filenames are derived from the model name.

---

💬 Talking to it with the CLI

python infer.py --base-url http://localhost:18000/v1 -v --max_new_tokens 2048

Interactive keys

• Ctrl-N: reset conversation
• Ctrl-C: quit

---

🌐 HTTP API

GET /v1/models

Returns a list with the currently loaded model:

{
  "object": "list",
  "data": [
    {
      "id": "Dracarys2-72B-Instruct-4bit",
      "object": "model",
      "created": 1727389042,
      "owned_by": "kamiwaza"
    }
  ]
}

The created field is set when the server starts and mirrors the OpenAI API's timestamp.

POST /v1/chat/completions

{
  "model": "Dracarys2-72B-Instruct-4bit",
  "messages": [
    { "role": "user",
      "content": [
        { "type": "text", "text": "Describe this image." },
        { "type": "image_url",
          "image_url": { "url": "data:image/jpeg;base64,..." } }
      ]
    }
  ],
  "max_tokens": 512,
  "stream": false
}

Response (truncated):

{
  "id": "chatcmpl-d4c5…",
  "object": "chat.completion",
  "created": 1715242800,
  "model": "Dracarys2-72B-Instruct-4bit",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "The image shows…" },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 143,
    "completion_tokens": 87,
    "total_tokens": 230,
    "tokens_per_second": 32.1
  }
}

Add "stream": true and you'll get Server-Sent Events chunks followed by data: [DONE].

Prompt Caching (Text-Only Models):

• Automatic prompt caching is controlled by server startup flags:
  • --enable-prefix-caching (defaults to True): When enabled, the server will cache system messages for reuse across requests.
  • --prompt-cache-dir (defaults to ./.cache/mlx_prompt_caches/): This directory is used to store and load cache files. Cache filenames are automatically generated based on the model name (e.g., Qwen3-8B-4bit.safetensors).
• Behavior:
  1. The server caches only the system message portion of conversations, not the entire prompt.
  2. When a request contains a system message, the server:
     • Creates a cache of the system message on first use
     • Reuses this cache for subsequent requests with the same system message
     • Only processes the new user messages, dramatically improving performance
  3. The cache is automatically discarded and recreated if the system message changes.
  4. This is ideal for scenarios like:
     • Chatbots with fixed system prompts
     • Question-answering over long documents (document in system message)
     • Any use case where the system context remains constant across requests
• Example: If your system message contains a 10,000 token document, only the first request processes all tokens. Subsequent questions about the document only process the new user message tokens.
• This process is transparent to the API client; no special parameters are needed.
• This feature is only applicable to text-only models.

---

🛠️ Internals (two-sentence tour)

• server.py – loads the model with mlx-vlm, converts incoming OpenAI vision messages to the model's chat-template, handles images / video frames, and streams tokens back. For text-only models, if enabled via server flags, it automatically manages a system message cache to speed up processing when multiple queries reference the same system context.
• infer.py – lightweight REPL that keeps conversation context and shows latency / TPS stats.

That's it – drop it in front of any MLX model and start chatting!