Tags: jw3126/ONNXRunTime.jl
Tags
[Diff since v1.3.0](v1.3.0...v1.3.1) **Merged pull requests:** - Uncommenting Bool (#42) (@dstarkenburg)
[Diff since v1.1.1](v1.1.1...v1.2.0) **Merged pull requests:** - Logging level (#39) (@GunnarFarneback)
[Diff since v1.1.0](v1.1.0...v1.1.1) **Merged pull requests:** - Upper bound cuDNN compat (#38) (@GunnarFarneback) **Closed issues:** - Incompatibility with cuDNN 1.3.1 (#37)
[Diff since v1.0.0](v1.0.0...v1.1.0) **Merged pull requests:** - Support CUDA provider options. (#36) (@GunnarFarneback)
[Diff since v0.4.0](v0.4.0...v0.4.1) **Merged pull requests:** - High level release function (#34) (@GunnarFarneback) **Closed issues:** - Manual release of memory (#33)
[Diff since v0.3.0](v0.3.0...v0.3.1) **Closed issues:** - Error: could not load library ... onnxruntime.dll ... The specified module could not be found. (#18) - Incorrect results for matrix multiplication (#21) **Merged pull requests:** - make input_names and output_names fields of InferenceSession public (#16) (@jw3126) - CompatHelper: bump compat for DocStringExtensions to 0.9, (keep existing compat) (#17) (@github-actions[bot]) - added check to prevent CUDA driver activation if CUDA is not functional (#23) (@rssdev10) - update onnxruntime to v1.31.1 (#24) (@jw3126) - Fix Mac aarch64 artifacts (#25) (@rssdev10)
PreviousNext