ROCm/FastFlowLM v1.0.6

Release v1.0.6

on GitHub

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:52625/v1",
    api_key="dummykey",  # FLM runs locally; the key is not checked
)

# Keep everything fixed in the system prompt — it is prefilled once and
# reused across requests. Vary only the user message.
SYSTEM_PROMPT = "You are a concise assistant. Answer in one short sentence."

for question in ["Why is the sky blue?", "Why is grass green?"]:
    print(f"\n> {question}")
    stream = client.chat.completions.create(
        model="gemma4e-flash:e2b",
        messages=[
            {"role": "system", "content": SYSTEM_PROMPT},   # same every time
            {"role": "user", "content": question},          # only this changes
        ],
        stream=True,
    )
    for chunk in stream:
        delta = chunk.choices[0].delta.content
        if delta:
            print(delta, end="", flush=True)
    print()

import base64
from openai import OpenAI

image_path = r"C:\path\to\image.png"   # <-- edit this

client = OpenAI(base_url="http://127.0.0.1:52625/v1", api_key="dummykey")

with open(image_path, "rb") as image_file:
    image = base64.b64encode(image_file.read()).decode("utf-8")

stream = client.chat.completions.create(
    model="qwen3vl-flash:4b",
    messages=[
        {"role": "system", "content": "Describe images in one sentence."},
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{image}"},
                },
            ],
        },
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()

import base64
from openai import OpenAI

audio_path = r"C:\path\to\audio.wav"   # <-- edit this

client = OpenAI(base_url="http://127.0.0.1:52625/v1", api_key="dummykey")

with open(audio_path, "rb") as audio_file:
    audio = base64.b64encode(audio_file.read()).decode("utf-8")

stream = client.chat.completions.create(
    model="gemma4e-flash:e2b",
    messages=[
        {"role": "system", "content": "Transcribe and summarize audio briefly."},
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is said in this clip?"},
                {
                    "type": "input_audio",
                    "input_audio": {"data": audio},
                },
            ],
        },
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()

import base64
from openai import OpenAI

audio_path = r"C:\path\to\audio.wav"   # <-- edit this
image_path = r"C:\path\to\image.png"   # <-- edit this

client = OpenAI(base_url="http://127.0.0.1:52625/v1", api_key="dummykey")

with open(audio_path, "rb") as audio_file:
    audio = base64.b64encode(audio_file.read()).decode("utf-8")
with open(image_path, "rb") as image_file:
    image = base64.b64encode(image_file.read()).decode("utf-8")

stream = client.chat.completions.create(
    model="gemma4e-flash:e2b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Finish two tasks: 1. Summarize the audio. 2. Describe the image."},
                {
                    "type": "input_audio",
                    "input_audio": {"data": audio},
                },
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{image}"},
                },
            ],
        }
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()