Stars
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
The Triton TensorRT-LLM Backend
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Layout-Guided multi-view driving scene video generation with latent diffusion model
深度学习入门教程, 优秀文章, Deep Learning Tutorial