Files
wehub-resource-sync 59a0a3844c
PR Test AMD / cancel-on-close (push) Has been skipped
PR Test NVIDIA ARM / scan (push) Has been skipped
PR Test NVIDIA / cancel-on-close (push) Has been skipped
PR Test AMD / scan (push) Has been skipped
PR Test NVIDIA ARM / cancel-on-close (push) Has been skipped
PR Test NVIDIA / scan (push) Has been skipped
Release Docker Images / build (cu129-torch-2.11.0) (push) Has been skipped
Release Docker Images / build (cu130-torch-2.11.0) (push) Has been skipped
Release PyPI / publish (push) Has been skipped
Scheduler Python Test / test (push) Successful in 27m19s
Docs / build (push) Successful in 28m8s
Scheduler C++ Test / test (push) Successful in 28m19s
Scheduler C++ Test / test-flat (push) Successful in 28m18s
Docs / deploy (push) Has been cancelled
PR Test AMD / finish (push) Has been cancelled
PR Test NVIDIA / finish (push) Has been cancelled
PR Test NVIDIA ARM / finish (push) Has been cancelled
PR Test NVIDIA ARM / ${{ matrix.name }} (${{ matrix.runner }}) (push) Has been cancelled
PR Test AMD / ${{ matrix.name }} (${{ matrix.runner }}) (push) Has been cancelled
PR Test NVIDIA / ${{ matrix.name }} (${{ matrix.runner }}) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:32:31 +08:00

49 lines
1.1 KiB
Markdown

# Acknowledgements
TokenSpeed builds on a broad open source ecosystem. We are grateful to the
projects and contributors whose work is acknowledged in our package-level
third-party notices.
## tokenspeed
The `tokenspeed` Python package acknowledges and thanks:
- `NVIDIA/TensorRT-LLM`
- `meituan-longcat/SGLang-FluentLLM`
- `vllm-project/vllm`
- `ModelTC/lightllm`
- `sgl-project/sglang`
## tokenspeed-kernel
The `tokenspeed-kernel` package acknowledges and thanks:
- `NVIDIA/TensorRT-LLM`
- `triton-lang/triton`
- `deepseek-ai/DeepEP`
- `deepseek-ai/DeepGEMM`
- `Dao-AILab/flash-attention`
- `deepseek-ai/FlashMLA`
- `Dao-AILab/fast-hadamard-transform`
- `sgl-kernel`
- `flashinfer-ai/flashinfer`
## tokenspeed-mla
The `tokenspeed-mla` package acknowledges and thanks:
- `NVIDIA/cutlass`
- `flashinfer-ai/flashinfer`
## License Notices
We follow open source license requirements by keeping package-level
`THIRDPARTYNOTICES` files with the relevant third-party notices and license
texts. For Python packages built with setuptools, these files are included in
the package metadata with:
```toml
[tool.setuptools]
license-files = ["LICENSE", "THIRDPARTYNOTICES"]
```