SOTA Multi-Head Self-Attention benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
CUDA-LLM kernels task suite Multi-Head Self-Attention	OptiML	Execution Time (s)6.85	5	3d ago
CUDA-LLM kernels task suite 1.0 (test)	OptiML	Execution Time6.85	5	3d ago
CUDA-LLM kernels task suite (test)	-	Latency (s)-	0	5d ago

Showing 3 of 3 rows