Gahow Wang
d77f921a12
- Naive GEMM kernel: one thread per output element (F32 + BF16) - Tiled GEMM kernel: 32x32 shared memory tiles (F32 + BF16) - cuBLAS wrapper: cublasGemmEx with row-major trick - GemmBackend enum for runtime backend selection - CublasContext RAII handle - Made error::check public for cross-crate use - 17 GEMM tests: small/medium/rect sizes, all backends, F32+BF16 - Cross-backend consistency verified (naive vs tiled vs cuBLAS) - All 44 tests pass across all crates Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
17 lines
245 B
TOML
17 lines
245 B
TOML
[workspace]
|
|
resolver = "2"
|
|
members = [
|
|
"crates/xserv-cuda",
|
|
"crates/xserv-tensor",
|
|
"crates/xserv-kernels",
|
|
]
|
|
|
|
[workspace.package]
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
license = "MIT"
|
|
|
|
[workspace.dependencies]
|
|
half = "2"
|
|
smallvec = "1"
|