- 07 8月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 06 8月, 2023 2 次提交
-
-
由 JeremyRand 提交于
* Add POWER8 VSX toolchains POWER8, though slower than POWER9, is still used in the wild; these toolchains should still be much faster on POWER8 than POWER8 without VSX optimizations. * VSX toolchains: set -cpu arg in QEMU CI tests
-
由 mizu-bai 提交于
-
- 05 8月, 2023 1 次提交
-
-
由 Han Gao 提交于
-
- 04 8月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 03 8月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 01 8月, 2023 2 次提交
- 31 7月, 2023 1 次提交
-
-
由 Han Gao 提交于
-
- 27 7月, 2023 1 次提交
-
-
由 nihui 提交于
* enable VK_KHR_cooperative_matrix * add khr cm shader * update glslang * print matrix info
-
- 26 7月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 24 7月, 2023 1 次提交
-
-
由 nihui 提交于
Tensor.fill Tensor.index_put Tensor.to Tensor.type_as torch.topk fmod call Tensor member functions with inputnames static shape_as_tensor nn.Linear dynamic bias eliminate noop type_as convert two-dim nn.Linear to ncnn gemm convert torch.stack to ncnn concat+reshape ignore torch einsum path input
-
- 22 7月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 21 7月, 2023 1 次提交
-
-
由 ฅ'ω'ฅ 提交于
-
- 18 7月, 2023 1 次提交
-
-
由 Mek101 提交于
-
- 16 7月, 2023 1 次提交
-
-
由 Mek101 提交于
-
- 15 7月, 2023 1 次提交
-
-
由 Mek101 提交于
-
- 11 7月, 2023 3 次提交
-
-
由 Upliner Mikhalych 提交于
-
由 nihui 提交于
-
由 JeremyRand 提交于
Improves compatibility with Clang 11. Also rename NCNN_SSE* options to NCNN_VSX_SSE* to avoid conflict between x86 and POWER (went unnoticed before because x86 doesn't have an option for toggling SSE 4.1). Co-authored-by: NJeremy Rand <jeremyrand@danwin1210.de>
-
- 10 7月, 2023 3 次提交
-
-
由 nihui 提交于
-
由 dependabot[bot] 提交于
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel) from 2.13.0 to 2.13.1. - [Release notes](https://github.com/pypa/cibuildwheel/releases) - [Changelog](https://github.com/pypa/cibuildwheel/blob/main/docs/changelog.md) - [Commits](https://github.com/pypa/cibuildwheel/compare/v2.13.0...v2.13.1) --- updated-dependencies: - dependency-name: pypa/cibuildwheel dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: Ndependabot[bot] <support@github.com> Co-authored-by: Ndependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
-
由 Zhang Geng 提交于
-
- 06 7月, 2023 2 次提交
-
-
由 nihui 提交于
* fix build, prepend batch for broadcast reshape * sanitize filename * do not fuse to eltwise if broadcast
-
由 JeremyRand 提交于
* Add POWER9 VSX toolchains Translating x86_64 SSE to ppc64le VSX intrinsics yields a quite large speedup on POWER9. See this article for background: https://www.talospace.com/2019/07/easier-power-vectorizing-for-fun-and.html * Add power9le docs * power9le clang toolchain: Document Clang 13+ requirement --------- Co-authored-by: NJeremy Rand <jeremyrand@danwin1210.de>
-
- 04 7月, 2023 1 次提交
-
-
由 Kin Yu Shek 提交于
-
- 03 7月, 2023 1 次提交
-
-
由 未知时光 提交于
-
- 02 7月, 2023 1 次提交
-
-
由 張小凡 提交于
-
- 27 6月, 2023 2 次提交
- 26 6月, 2023 2 次提交
- 25 6月, 2023 1 次提交
-
-
由 nihui 提交于
* update riscv qemu * c906 test on qemu * fix qemu aarch64
-
- 23 6月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 20 6月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 19 6月, 2023 1 次提交
-
-
由 nihui 提交于
* simplify binaryop * less gpu test * update binaryop broadcast doc * do not test atan2 zero
-
- 15 6月, 2023 1 次提交
-
-
由 nihui 提交于
-
- 14 6月, 2023 1 次提交
-
-
由 Zhenjia Guo 提交于
-
- 12 6月, 2023 2 次提交
-
-
由 Zhang Geng 提交于
-
由 nihui 提交于
* write shape, fuse sam image encoder attention * set more dynamic shape as static * less warning for constant tensor node
-