1 Repo
Writes GEMV kernels that tile the vector and matrix into shared memory for efficient data reuse.
Distinct from Tile-Based Kernel Authoring: Distinct from Tile-Based Kernel Authoring: focuses on GEMV-specific tiling, not general tile-based kernel authoring.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · GEMV Shared Memory Tilers. Refine with filters or upvote what's useful.
TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc
Writes GEMV kernels that tile the vector and matrix into shared memory for efficient data reuse.