pip install dflash-mlx

# or isolated install
pipx install dflash-mlx

# Auto-resolve draft model from registry
dflash --model Qwen/Qwen3.5-9B --prompt "Explain backpropagation"

# Explicit draft model
dflash --model Qwen/Qwen3.5-9B \
       --draft z-lab/Qwen3.5-9B-DFlash \
       --prompt "Explain backpropagation"

# Disable EOS (useful for benchmarking fixed token counts)
dflash --model Qwen/Qwen3.5-9B --prompt "..." --max-tokens 1024 --no-eos

# Basic server
dflash-serve --model Qwen/Qwen3.5-9B --port 8000

# With explicit draft
dflash-serve --model Qwen/Qwen3.5-9B \
             --draft z-lab/Qwen3.5-9B-DFlash \
             --port 8000

# Disable thinking/reasoning tokens (Qwen3.5 thinking models)
dflash-serve --model Qwen/Qwen3.5-9B --port 8000 \
  --chat-template-args '{"enable_thinking": false}'

# Raise fallback threshold for longer prompts (large models)
dflash-serve --model mlx-community/Qwen3.5-35B-A3B-4bit --port 8000 \
  --chat-template-args '{"enable_thinking": false}' \
  --dflash-max-ctx 16384

dflash-benchmark \
  --model Qwen/Qwen3.5-9B \
  --draft z-lab/Qwen3.5-9B-DFlash \
  --prompt "The function f satisfies..." \
  --max-tokens 1024 \
  --repeat 3 \
  --no-eos

from dflash_mlx import DFlashRuntime

runtime = DFlashRuntime.from_pretrained(
    model="Qwen/Qwen3.5-9B",
    draft="z-lab/Qwen3.5-9B-DFlash",  # optional, auto-resolved
)

prompt = "Explain the Pythagorean theorem step by step."

for token_text in runtime.stream_generate(
    prompt=prompt,
    max_tokens=512,
    use_chat_template=True,
):
    print(token_text, end="", flush=True)
print()

from dflash_mlx import DFlashRuntime

runtime = DFlashRuntime.from_pretrained(model="Qwen/Qwen3.5-9B")

result = runtime.generate(
    prompt="What is speculative decoding?",
    max_tokens=256,
    use_chat_template=True,
)

print(result.text)
print(f"Tokens/sec: {result.tokens_per_second:.2f}")
print(f"Acceptance rate: {result.acceptance_rate:.2%}")
print(f"Total tokens: {result.total_tokens}")

from dflash_mlx import DFlashRuntime, DFlashConfig

config = DFlashConfig(
    draft_block_size=16,      # tokens drafted per speculative step
    max_ctx=8192,             # max context length before fallback
    enable_tape_replay=True,  # GatedDeltaNet recurrent rollback
    jit_sdpa=True,            # custom Metal SDPA for long contexts
)

runtime = DFlashRuntime.from_pretrained(
    model="mlx-community/Qwen3.5-27B-4bit",
    config=config,
)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="not-needed",  # dflash-serve does not require auth by default
)

# Non-streaming
response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[
        {"role": "user", "content": "Explain gradient descent."}
    ],
    max_tokens=512,
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[{"role": "user", "content": "Write a haiku about silicon."}],
    max_tokens=128,
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)
print()

import json
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a city",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"},
                },
                "required": ["city"],
            },
        },
    }
]

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto",
)

tool_call = response.choices[0].message.tool_calls[0]
print(f"Function: {tool_call.function.name}")
print(f"Args: {json.loads(tool_call.function.arguments)}")

PYTHONPATH=. python3 -m examples.demo --mode dflash \
  --target-model Qwen/Qwen3.5-9B \
  --draft-model z-lab/Qwen3.5-9B-DFlash \
  --prompt "Solve: f(x) + f(y) = f(x+y) - xy - 1" \
  --max-tokens 2048 \
  --no-eos

# Force a custom draft — bypasses registry check
dflash --model my-org/MyCustomModel \
       --draft my-org/MyCustomModel-DFlash \
       --prompt "Hello"

# CLI
dflash --model Qwen/Qwen3.5-9B \
       --chat-template-args '{"enable_thinking": false}' \
       --prompt "What is 2+2?"

# Server
dflash-serve --model Qwen/Qwen3.5-9B \
             --chat-template-args '{"enable_thinking": false}' \
             --port 8000

Error: No DFlash draft found for model 'org/ModelName'

# Check port is not in use
lsof -i :8000

# Bind to all interfaces for network access
dflash-serve --model Qwen/Qwen3.5-9B --port 8000 --host 0.0.0.0

ls benchmark/results/
# Per-run JSON with tok/s, acceptance rate, repeat measurements