Instructions to use OpenGVLab/InternVL2-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-8B", 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("OpenGVLab/InternVL2-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenGVLab/InternVL2-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-8B",
		"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/OpenGVLab/InternVL2-8B

SGLang

How to use OpenGVLab/InternVL2-8B 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 "OpenGVLab/InternVL2-8B" \
    --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": "OpenGVLab/InternVL2-8B",
		"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 "OpenGVLab/InternVL2-8B" \
        --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": "OpenGVLab/InternVL2-8B",
		"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 OpenGVLab/InternVL2-8B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-8B
```

Fail to run BNB 8-bit Quantization version of "OpenGVLab/InternVL2-8B" on Jetson AGX Orin

#14

by cyu021 - opened Aug 17, 2024

Discussion

cyu021

Aug 17, 2024

I fail to run BNB 8-bit Quantization version of "OpenGVLab/InternVL2-8B" on Jetson AGX Orin with the following error message:

Exception in thread Thread-3 (chat_with_hist):
Traceback (most recent call last):
File "/usr/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
File "/usr/lib/python3.11/threading.py", line 982, in run
self._target(*self._args, **self._kwargs)
File "/data/myllm/MultilingualE5large_2_2.py", line 130, in chat_with_hist
response, history = models[0].chat(tokenizer, None, "hello, this is james", generation_config, history=None, return_history=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internvl_chat.py", line 286, in chat
generation_output = self.generate(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internvl_chat.py", line 336, in generate
outputs = self.language_model.generate(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/transformers/generation/utils.py", line 2024, in generate
result = self._sample(
^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/transformers/generation/utils.py", line 2982, in _sample
outputs = self(**model_inputs, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/accelerate/hooks.py", line 169, in new_forward
output = module._old_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internlm2.py", line 1068, in forward
outputs = self.model(
^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/accelerate/hooks.py", line 169, in new_forward
output = module._old_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internlm2.py", line 953, in forward
layer_outputs = decoder_layer(
^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/accelerate/hooks.py", line 169, in new_forward
output = module._old_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internlm2.py", line 656, in forward
hidden_states, self_attn_weights, present_key_value = self.attention(
^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/accelerate/hooks.py", line 169, in new_forward
output = module._old_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internlm2.py", line 498, in forward
attn_output = self._flash_attention_forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/InternVL2-8B/3bfd3664dea4f3da628785f5125d30f889701253/modeling_internlm2.py", line 557, in _flash_attention_forward
attn_output = flash_attn_func(
^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/flash_attn/flash_attn_interface.py", line 880, in flash_attn_func
return FlashAttnFunc.apply(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/autograd/function.py", line 574, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/flash_attn/flash_attn_interface.py", line 546, in forward
out, q, k, v, out_padded, softmax_lse, S_dmask, rng_state = _flash_attn_forward(
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/flash_attn/flash_attn_interface.py", line 52, in _flash_attn_forward
out, q, k, v, out_padded, softmax_lse, S_dmask, rng_state = flash_attn_cuda.fwd(
^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: invalid device function
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

===========================================================
Following is my env configuration:
Module: NVIDIA Jetson AGX Orin (64GB ram)
OS: Ubuntu 20.04 Focal Fossa
CUDA Arch BIN: 8.7
L4T: 35.3.1
Jetpack: 5.1.1
CUDA: 11.8.89
cuDNN: 8.6.0.166
Python: 3.11.9
torch: 2.4.0
torchvision: 0.19.0
flash_attn: 2.6.3

any ideas?

zwgao

OpenGVLab org Aug 23, 2024

It looks like the CUDA kernel function is not compatible with the device architecture. Unfortunately we cannot reproduce the bug because we do not have a Jetson AGX Orin device. Please verify that flash_attn is compiled successfully and supports NVIDIA Jetson AGX Orin.

czczup changed discussion status to closed Sep 4, 2024

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