[VLM][Model] Support image input for Chameleon #6633
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
70 tasks
|
This PR is ready to be reviewed and tested. Below is an example modified from the Chameleon PR on from vllm import LLM, SamplingParams
import torch
from PIL import Image
import requests
model_path = "facebook/chameleon-30b"
llm = LLM(model=model_path, dtype=torch.bfloat16, max_num_seqs=10)
image = Image.open(requests.get("https://uploads4.wikiart.org/images/paul-klee/death-for-the-idea-1915.jpg!Large.jpg", stream=True).raw)
greedy_params = SamplingParams(temperature=0.0, max_tokens=40)
prompt = "I'm very intrigued by this work of art:<image>Please tell me about the artist."
output = llm.generate(
{"prompt": prompt,
"multi_modal_data": {"image": image}
},
greedy_params)
print(output[0].outputs[0].text)Output On main branch of import torch
from PIL import Image
import requests
from transformers import (
ChameleonConfig,
ChameleonForConditionalGeneration,
ChameleonImageProcessor,
ChameleonProcessor,
)
model_path = "facebook/chameleon-30b"
model = ChameleonForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.bfloat16, device_map="auto")
processor = ChameleonProcessor.from_pretrained(model_path)
prompt = "I'm very intrigued by this work of art:<image>Please tell me about the artist."
image = Image.open(requests.get("https://uploads4.wikiart.org/images/paul-klee/death-for-the-idea-1915.jpg!Large.jpg", stream=True).raw)
inputs = processor(prompt, images=[image], return_tensors="pt").to(model.device, dtype=torch.bfloat16)
length = inputs.input_ids.shape[1]
out = model.generate(**inputs, max_new_tokens=40, do_sample=False)
generated_text = processor.batch_decode(out[:, length:], skip_special_tokens=False)[0]
print(generated_text)Output |
|
It would be great if you could add a test case for inputting images into Chameleon! |
|
Running into an OOM error under default setting. A100 - 80G, 7B Chameleon model. Code Stacktrace I think there is something wrong with the profiling logic. Especially considering the hardware is pretty generous for the size of the model run. |
Thank you for catching this - this has been fixed! |
xwjiang2010
reviewed
Jul 23, 2024
xwjiang2010
reviewed
Jul 23, 2024
xwjiang2010
reviewed
Jul 23, 2024
xwjiang2010
reviewed
Jul 23, 2024
|
I am done with manual testing. |
|
I have addressed all comments and added a batched test! cc @xwjiang2010 @DarkLight1337 |
DarkLight1337
approved these changes
Jul 23, 2024
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Jul 24, 2024
cduk
pushed a commit
to cduk/vllm-pascal
that referenced
this pull request
Aug 6, 2024
kylesayrs
pushed a commit
to neuralmagic/vllm
that referenced
this pull request
Aug 17, 2024
DarkLight1337
changed the title
Alvant
pushed a commit
to compressa-ai/vllm
that referenced
this pull request
Oct 26, 2024
Signed-off-by: Alvant <alvasian@yandex.ru>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is a follow-up to #5770 that adds image + text -> text support for Chameleon. Current implementation only allows one image per request.
FIXES #5721
PR Checklist (Click to Expand)
Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]for bug fixes.[CI/Build]for build or continuous integration improvements.[Doc]for documentation fixes and improvements.[Model]for adding a new model or improving an existing model. Model name should appear in the title.[Frontend]For changes on the vLLM frontend (e.g., OpenAI API server,LLMclass, etc.)[Kernel]for changes affecting CUDA kernels or other compute kernels.[Core]for changes in the core vLLM logic (e.g.,LLMEngine,AsyncLLMEngine,Scheduler, etc.)[Hardware][Vendor]for hardware-specific changes. Vendor name should appear in the prefix (e.g.,[Hardware][AMD]).[Misc]for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
format.shto format your code.docs/source/if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-requiredand might not go through the PR.What to Expect for the Reviews
The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:
action-requiredlabel on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!