biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Guide for Incremental Compilation Workflow (#19109)

Browse Source
This commit is contained in:
Michael Goin
2025-06-25 22:06:46 +09:00
committed by GitHub
parent c53fec1fcb
commit bf5181583f
4 changed files with 313 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/contributing/README.md
View File

@@ -29,6 +29,8 @@ See <gh-file:LICENSE>.
Depending on the kind of development you'd like to do (e.g. Python, CUDA), you can choose to build vLLM with or without compilation.
Check out the [building from source][build-from-source] documentation for details.
For an optimized workflow when iterating on C++/CUDA kernels, see the [Incremental Compilation Workflow](./incremental_build.md) for recommendations.
### Building the docs with MkDocs
#### Introduction to MkDocs
@@ -188,6 +190,7 @@ The PR needs to meet the following code quality standards:
### Adding or Changing Kernels
When actively developing or modifying kernels, using the [Incremental Compilation Workflow](./incremental_build.md) is highly recommended for faster build times.
Each custom kernel needs a schema and one or more implementations to be registered with PyTorch.
- Make sure custom ops are registered following PyTorch guidelines: