Romaosir/flash-attention
Fast and memory-efficient exact attention
Repositories
Romaosir/IF_Romao_kernel_optimize
skills, prompts
Romaosir/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Romaosir/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.