Gahow Wang
1384044f27
Forward: hand-written tiled GEMM vs cuBLAS sgemm on random matrices (square / non-tile-aligned rect / 256³), max relative error < 1e-3, using the row-major⟺col-major identity to drive cuBLAS without explicit transposes. Backward: scalar loss L = sum(W∘C) (so dC = W), dA/dB from matmul_backward checked against the finite-diff harness. Gated behind not(no_cuda). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
13 lines
259 B
TOML
13 lines
259 B
TOML
[package]
|
|
name = "xtrain-tensor"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
|
|
[dependencies]
|
|
xtrain-cuda = { path = "../xtrain-cuda" }
|
|
half.workspace = true
|
|
smallvec.workspace = true
|
|
|
|
[dev-dependencies]
|
|
xtrain-autodiff = { path = "../xtrain-autodiff" }
|