Add silu-mul to rms-norm fusion #20
Conversation
|
👋 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:
🚀 |
| result = torch.empty(x.shape[0], x.shape[1] // 2, device=x.device, dtype=torch.float8_e4m3fn) | ||
|
|
||
| torch.ops._C.silu_and_mul_quant(result, x, scale) | ||
| return result |
There was a problem hiding this comment.
The double dispatching might be hurting us here. Is there some reason we can't just inline this pattern into the replacement?
There was a problem hiding this comment.
I'll let @Sage confirm but I think this is hiding the slice issue
There was a problem hiding this comment.
Or see if we can call torch.ops._C.silu_and_mul_quant.default directly? (if we make sure that this only gets applied for CUDA)
| x = torch.empty((128, 256), device="cuda", dtype=torch.float16) | ||
| scale = torch.empty((1,1), device="cuda" , dtype=torch.float32) |
There was a problem hiding this comment.
Do we need to set device/type here? I guess it doesn't matter a whole lot since I think these are mostly ignored
There was a problem hiding this comment.
This was just sage's diff I added. I would not land this without fully removing the allocations from patterns
FILL IN THE PR DESCRIPTION HERE
FIX #xxxx (link existing issues this PR will resolve)
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!