Download Latest Version v3.14.1 source code.zip (20.2 MB)
Home / v3.13.4
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-10-06 1.1 kB
1 1 weekly downloads
v3.13.4 source code.tar.gz 2026-10-06 14.3 MB
1 1 weekly downloads
v3.13.4 source code.zip 2026-10-06 17.9 MB
1 1 weekly downloads
Totals: 3 Items   32.2 MB 3

This is a patch release containing the following changes to v3.13.3:

  • Fixed crash in grouped matmul with large shapes on Intel GPUs based on Xe architecture (bb0e26c9d55a96ab31202d8332c47aa210193523, 93e82fc3b7f787ba881c7fb7a65fc208f06e46d4, e81aa2481fa051b332d517c59215b73da525cc8b, 1411796109c72d9317943d59afd2347a99227453, c899370a004ecd822708f89b2c3581361955e14a, b93345904a786d96e58fd231bb9fc17bcf14ff6a, a93026cc0f0d1afabd8d034ed8d8f02f32021b1a)
  • Fixed correctness issue in f16, bf16, and s8/u8 convolutions with small number of input channels on x64 processors with Intel AMX instruction set support (fed7e418d106de3e405fe3330fd75d684c9332b5)
  • Fixed correctness issue in f16, bf16, and s8/u8 convolutions with trivial output width on x64 processors with Intel AMX instruction set support (8b5f0abb15ea379777b7f3bb38798d12bd846335, e5cb5ff327e79caa9074ff2e0cb90ab146fb3e43)
  • Fixed correctness issue in f32 convolution weight gradienton x64 processors with Intel AVX-512 instruction set support (425603361167c9a6bd1c991c1efcd0e7b4c72a9d)
Source: README.md, updated 2026-10-06