Alternatives to gpu-mode/reference-kernels

gpu-mode/reference-kernels: Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard! No license declared. Below, the open repos Take My Repo keeps on the same subjects, most starred first. Stars measure popularity, not quality.

AI on my own machineRepo

SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

  • 4k
  • Cuda
  • Apache-2.0
  • 10 mo ago
thu-mlTake it

Side by side

NameStarsLicenseLanguageLast changeIn commonCompare
gpu-mode/reference-kernels332None declaredPython7 d ago
debpalash/VoiceStudio116kAGPL-3.0Python4 h agocudaCompare
pytorch/pytorch106kNone declaredPython11 h agogpuCompare
Cloud-CV/EvalAI2kNone declaredPython9 d agoleaderboardCompare
linkedin/Liger-Kernel6.7kBSD-2-ClausePython3 d agotritonCompare
vllm-project/vllm97kApache-2.0Python4 h agocudaCompare
alacritty/alacritty66kApache-2.0Rust4 d agogpuCompare
tatsu-lab/alpaca_eval2kApache-2.0Jupyter Notebook16 mo agoleaderboardCompare
thu-ml/SageAttention4kApache-2.0Cuda10 mo agocuda, tritonCompare
jamiepine/voicebox61kMITPython1 d agocudaCompare
exelban/stats44kMITSwift2 d agogpuCompare
THUDM/CogDL1.8kMITPython3 y agoleaderboardCompare
Zaneham/Booth1.8kApache-2.0C4 wk agocuda, gpu, tritonCompare

Read from GitHub and Hugging Face. A value a source does not give is shown as unknown, never guessed.

Get , open it once and sign in. Then come back here and press the button again.

gpu-mode/reference-kernels alternatives: similar open source repos on Take My Repo