Instructions to use amd/Kimi-K2.5-W4A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Kimi-K2.5-W4A8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="amd/Kimi-K2.5-W4A8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("amd/Kimi-K2.5-W4A8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use amd/Kimi-K2.5-W4A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Kimi-K2.5-W4A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Kimi-K2.5-W4A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Kimi-K2.5-W4A8

SGLang

How to use amd/Kimi-K2.5-W4A8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "amd/Kimi-K2.5-W4A8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Kimi-K2.5-W4A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "amd/Kimi-K2.5-W4A8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Kimi-K2.5-W4A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use amd/Kimi-K2.5-W4A8 with Docker Model Runner:
```
docker model run hf.co/amd/Kimi-K2.5-W4A8
```

Fix tokenization_kimi.py bytes_to_unicode import for transformers v5+

by Jin-2025 - opened 16 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-1

Jin-2025

AMD org 16 days ago

tokenization_kimi.py (loaded via trust_remote_code=True) imports bytes_to_unicode from transformers.models.gpt2.tokenization_gpt2, but in transformers >= 5.0 the helper was relocated to transformers.convert_slow_tokenizer and the GPT-2 module no longer re-exports it, so loading the Kimi tokenizer crashes during vLLM startup with:

ImportError: cannot import name 'bytes_to_unicode' from
'transformers.models.gpt2.tokenization_gpt2'

This blocks serving amd/Kimi-K2.5-W4A8 on any image shipping transformers v5+ (e.g. vllm/vllm-openai-rocm:v0.19.1 and its subsequent version).

Fix

One-line change to import bytes_to_unicode from transformers.convert_slow_tokenizer instead:

-from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+from transformers.convert_slow_tokenizer import bytes_to_unicode

The function itself is byte-for-byte unchanged — only its public import path moved — and the new path also exists in transformers v4, so the fix is forward- and backward-compatible.

Verification

Running:

vllm serve /models/Kimi-K2.5-W4A8 --tensor-parallel-size 8 ...

on vllm/vllm-openai-rocm:v0.19.1 now loads the tokenizer successfully and startup proceeds to model loading.

Fix tokenization_kimi.py bytes_to_unicode import for transformers v5+3a971823

bowenbaoamd changed pull request status to merged 16 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment