wehub-resource-sync
ec436095dd
Book-CI / test (macos-latest) (push) Waiting to run
Deploy / deploy (macos-latest) (push) Waiting to run
Deploy / deploy (ubuntu-latest) (push) Waiting to run
Deploy / deploy (windows-latest) (push) Waiting to run
Release to PyPI / Build & publish sglang-kt (push) Waiting to run
Release to PyPI / Build kt-kernel (Python 3.11) (push) Waiting to run
Release to PyPI / Build kt-kernel (Python 3.12) (push) Waiting to run
Release to PyPI / Publish kt-kernel to PyPI (push) Blocked by required conditions
Book-CI / test (ubuntu-latest) (push) Waiting to run
Book-CI / test (windows-latest) (push) Waiting to run
Release Fake Tag / publish (push) Waiting to run
18 lines
849 B
Markdown
18 lines
849 B
Markdown
# Frequently Asked Questions
|
|
|
|
## 1. SGLang "Using default MoE kernel config" warning at startup
|
|
|
|
When using kt-kernel with SGLang, you may see a warning like:
|
|
|
|
```
|
|
[2026-05-15 20:31:38] Using default MoE kernel config. Performance might be sub-optimal!
|
|
Config file not found at .../fused_moe_triton/configs/...
|
|
```
|
|
|
|
This warning is **expected and can be safely ignored**. kt-kernel replaces SGLang's built-in MoE implementation with its own CPU/GPU hybrid dispatch, so SGLang's fused-MoE Triton kernel configuration is never used. The warning is emitted by SGLang before kt-kernel takes over MoE execution and has no impact on performance or correctness.
|
|
|
|
## 2. Where can I find more help?
|
|
|
|
Check the [existing issues](https://github.com/kvcache-ai/ktransformers/issues) or open a [new one](https://github.com/kvcache-ai/ktransformers/issues/new).
|
|
|