diff --git a/hugo.toml b/hugo.toml
index 84ab872..56f0a74 100644
--- a/hugo.toml
+++ b/hugo.toml
@@ -36,7 +36,7 @@ disableKinds = ['taxonomy', 'term', 'rss', 'sitemap', '404']
[[params.repos]]
name = "ndarray"
- kind = "library · v0.44.0"
+ kind = "library · v0.45.0"
href = "https://github.com/go-ndarray/ndarray"
blurb = "The library, in 13 dtypes with NumPy 2 promotion. Creation (Zeros/Arange/Linspace/…), strided views, broadcasting elementwise + ufuncs, reductions (Sum in NumPy's pairwise order, within a stated error bound checked against math/big, from go-simd/floats; Max/ArgMax/CumSum/Clip/Where), manipulation (Reshape/Concatenate/Stack), linalg (MatMul/Dot) on go-blas/blas, a panel-packed cache-blocked GEMM with a go-asmgen SIMD-FMA micro-kernel, the same kernels as before v0.42.0 (NEON 4×8 on arm64, AVX2/FMA 6×8 on amd64, VSX 8×8 on ppc64le, LASX 8×8 on loong64, RVV 6×8 on riscv64, 4×8 on s390x), and a Workspace arena for loops (Use/Reset/Detach). Packages linalg, fft and random are numpy.linalg, numpy.fft and numpy.random."
[[params.repos]]
diff --git a/layouts/index.html b/layouts/index.html
index 1ea4c0e..28493be 100644
--- a/layouts/index.html
+++ b/layouts/index.html
@@ -104,11 +104,11 @@
Sum 0.76×, fft.FFT 0.64×, Ravel 0.35× NumPy's time), 19 more tiedSum 0.80×, fft.FFT 0.52×, Ravel 0.36× NumPy's time), 17 more tiedExp/Log, ports of Arm's optimized-routinesRavel (0.35× NumPy's time, a view since v0.44.0), Real (0.57×), SqrtInto (0.52×), the complex fft.FFT (0.64×) and Sum (0.76×); 19 more are ties, such as Exp (0.92×). Slower on 186, chiefly from:
+ Ravel (0.36× NumPy's time, a view since v0.44.0), Real (0.58×), SqrtInto (0.50×), the complex fft.FFT (0.52×) and Sum (0.80×); 17 more are ties, such as Exp (0.98×). Slower on 185, chiefly from:
Add 3.1× NumPy's time, where AddInto ties);Ceil 20×, Abs 12×);No cgo, no BLAS shim. A portable pure-Go core, multicore, with SIMD kernels on amd64, arm64, ppc64le, loong64, riscv64 and s390x and a Workspace arena that takes the garbage collector out of loops. Measured against NumPy one core against one core: faster on Sum, Exp, SqrtInto and the complex FFT, slower on 186 of 256 operations, which are being worked through. The numbers are on the performance page.
No cgo, no BLAS shim. A portable pure-Go core, multicore, with SIMD kernels on amd64, arm64, ppc64le, loong64, riscv64 and s390x and a Workspace arena that takes the garbage collector out of loops. Measured against NumPy one core against one core: faster on Sum, Exp, SqrtInto and the complex FFT, slower on 185 of 256 operations, which are being worked through. The numbers are on the performance page.