[Feature] Update benchmark_throughput.py to support image input #9851
Conversation
* Give the request tuple a name * Add helper message for --dataset flag Signed-off-by: Linkun Chen <github+anyscale@lkchen.net>
* This is preparation to support multi-modality input, by reusing existing TextPrompt structure * no significant metrics diff, see below - before: Throughput: 13.99 requests/s, 2933.11 total tokens/s, 2758.10 output tokens/s - after: Throughput: 13.99 requests/s, 2932.69 total tokens/s, 2757.70 output tokens/s - test command: `python benchmarks/benchmark_throughput.py --model mistral-community/pixtral-12b --max-model-len=8192 --dataset ../sharegpt4v_instruct_gpt4-vision_cap100k.json` Signed-off-by: Linkun Chen <github+anyscale@lkchen.net>
Signed-off-by: Linkun Chen <github+anyscale@lkchen.net>
This reverts commit 2623fea. Signed-off-by: Linkun Chen <github+anyscale@lkchen.net>
This reverts commit eb6e01b. Signed-off-by: Linkun Chen <github+anyscale@lkchen.net>
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
|
|
||
| is_multi_model = any( |
There was a problem hiding this comment.
| is_multi_model = any( | |
| is_multi_modal = any( |
| print("\033[91mWARNING\033[0m: Multi-modal request detected. " | ||
| "The following metrics is not accurate.") |
There was a problem hiding this comment.
| print("\033[91mWARNING\033[0m: Multi-modal request detected. " | |
| "The following metrics is not accurate.") | |
| print("\033[91mWARNING\033[0m: Multi-modal request detected. " | |
| "The following metrics is not accurate because image tokens are not counted. See vllm-project/vllm/issues/9778 for details") |
| assert isinstance(image_path, | ||
| str), "Only support single image input" |
There was a problem hiding this comment.
We could make a TODO to support multi-image inputs.
|
|
||
| Args: | ||
| question: The input question text to wrap with special tokens | ||
| model: The name of the model being used, to determine which special tokens to add |
There was a problem hiding this comment.
Please fix the format by running bash format.sh locally (and probably need to manually solve line too long errors in comments).
| model = model.lower() | ||
| if "pixtral" in model: | ||
| return f"<s>[INST]{question}\n[IMG][/INST]" | ||
| raise ValueError(f"Unsupported model {model}") |
There was a problem hiding this comment.
This is fine for now, but as a follow up we could consider leveraging HF tokenizer's chat template.
Update benchmark_throughput to support image input. Tested with ShareGPT4V
on top of #9779 to tackle #9778
BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE
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.Adding or changing kernels
Each custom kernel needs a schema and one or more implementations to be registered with PyTorch.
Tensorsrequire meta-functions. Meta-functions should be implemented and registered in python so that dynamic dims can be handled automatically. See above documents for a description of meta-functions.torch.libary.opcheck()to test the function registration and meta-function for any registered ops. Seetests/kernelsfor examples.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!
cc @comaniac @ywang96