Automate adding lightweight JIT CUDA kernels to SGLang's jit_kernel module.
npx skills add https://github.com/sqjian/sglang --skill add-jit-kernel-sqjian
Please help me install this Agent Skill. Skill: add-jit-kernel Source: https://github.com/sqjian/sglang/tree/main/.claude/skills/add-jit-kernel Command: npx skills add https://github.com/sqjian/sglang --skill add-jit-kernel-sqjian
Step-by-step guide to extend SGLang with a new lightweight JIT CUDA kernel using the jit_kernel module, enabling rapid iteration and deployment.
Follow the guide to implement a new JIT CUDA kernel by adding the kernel C++/CUDA source, Python wrapper, tests, and benchmarks, then run the provided CI-style tests to validate correctness.
High-intent search queries and answers about installing and using this skill.
To add a custom JIT CUDA kernel to SGLang, you implement the kernel source under jit_kernel/csrc/, create a Python wrapper for runtime exposure, and write corresponding tests and benchmarks. This ensures correct integration and rapid iteration.
The best way to validate tensor inputs and ensure safe kernel launches in SGLang is by using the TensorMatcher for input validation and device checks, combined with LaunchKernel for deterministic launches and AlignedVector for vectorized memory access.
No, the SGLang jit_kernel module is specifically designed for adding lightweight JIT CUDA kernels that do not rely on large dependencies, ensuring fast iteration and deployment without heavy external library requirements.
The SGLang JIT kernel workflow connects C++ and Python by implementing the kernel logic in C++/CUDA source files and exposing it to the runtime through a Python wrapper, structuring the process across C++, Python, and tests.
Yes, you need to write benchmarks and unit tests when extending SGLang with a new CUDA kernel. This validates correctness and measures performance on CUDA devices, running CI-style tests to ensure quality.
You should use AlignedVector and LaunchKernel in your SGLang JIT kernel to maximize memory bandwidth and ensure safe, deterministic launches. These primitives provide vectorized memory access and structured execution.
moirai-internalGuide users through adding a lightweight JIT CUDA kernel to SGLang's jit_kernel module.
spacecat2002Add and validate lightweight CUDA JIT kernels in SGLang's jit_kernel module.
dyyounggAdd a lightweight CUDA kernel to SGLang's jit_kernel module with validation and Python wrapper.
hey-kongAdd a JIT CUDA kernel to SGLang's jit_kernel module with Python wrapper and tests.
