ELS-RD/kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

cudacuda-kernelpytorchtransformertriton

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 8 months ago. Archived: read-only, no further updates.

	Repository	Stars	Language	License	Activity
1	NVIDIA/TensorRT-LLMTensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimization	★ 14.8k	Python	Other	Active
2	AUTOMATIC1111/stable-diffusion-webuiStable Diffusion web UI	★ 165.1k	Python	AGPL-3.0	Slowing
3	Comfy-Org/ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the w	★ 138.4k	Python	GPL-3.0	Active
4	debpalash/VoiceStudioVoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription &	★ 74.8k	Python	AGPL-3.0	Active
5	labmlai/annotated_deep_learning_paper_implementations🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback,	★ 67.6k	Python	MIT	Slowing
6	keras-team/kerasDeep Learning for humans	★ 64.4k	Python	Apache-2.0	Active
7	ultralytics/ultralyticsUltralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose esti	★ 62.6k	Python	AGPL-3.0	Active
8	CorentinJ/Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time	★ 60.2k	Python	Other	Slowing