gladiolus 1.1.0

What's Changed

The major changes compared to v1.0.0 are:

• A new FIFO depth optimizer for the Vitis backend by @steltze in #1037
• Expansion of the oneAPI backend by adding depthwise convolution and RNN State and Activation Quantizers by @laurilaatu in #1131 and #1195
• A new general transpose implementation for vivado/vitis by @calad0i in #1124, adapted for oneAPI by @jmitrevs in #1165
• New depthwise 1D and 2D implementations for the resource strategy for io_stream by @steltze in #1079

The full list of changes is:

• Don't overwrite already set accum_t, fix pointwise output resolution by @jmitrevs in #1146
• Split hgq tests and isolate qkeras tests to make tests run in under 1h by @JanFSchulte in #1153
• Depthwise convolution for oneAPI by @laurilaatu in #1131
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #1159
• Fix Vivado Accelerator missing partition factor variable by @bo3z in #1160
• Bug fixes for channel-last conversions in pytorch by @JanFSchulte in #1161
• Support Constant nodes in pytorch parser by @JanFSchulte in #1123
• oneAPI 2025.0 include changes by @laurilaatu in #1149
• Update Torch profiler by @jicampos in #1156
• Add general transpose for vivado/vitis by @calad0i in #1124
• remove np.float_ (deprecated in numpy>=2.0) by @calad0i in #1172
• add check for no inputs in insert_node by @jmitrevs in #1170
• added check for conv implementation by @jicampos in #1155
• Lazy converter imports and migrate to pyproject.toml by @calad0i in #1094
• Fix pytorch upsample parsing by @vloncar in #1186
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #1182
• Fixes for quantised RNNs in data type inconsistencies by @bo3z in #1171
• Support multiple outputs in pytorch parser by @JanFSchulte in #1151
• general transpose for oneAPI by @jmitrevs in #1165
• add option to not write tar.gz for oneAPI and Quartus by @jmitrevs in #1189
• Fix paths to weights in build_lib.sh for VivadoAccelator backend by @JanFSchulte in #1198
• Fix link to FAQ in README.md by @vloncar in #1201
• Update pull request template by @vloncar in #1202
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #1199
• oneAPI RNN State and Activation Quantizers by @laurilaatu in #1195
• put code_gen.h in custom namespace by @calad0i in #1104
• Fix typo in pyproject.toml by @JanFSchulte in #1204
• Adjust model output if last node is removed by @JanFSchulte in #1205
• remove old variables when moving of scales by @jmitrevs in #1206
• Initial values for the hidden/cell state for LSTM and GRU models in Pytorch by @JanFSchulte in #1120
• Depthwise 1D and 2D Resource strategy for io_stream by @steltze in #1079
• make test_activations less sensitive to random seed values by @jmitrevs in #1211
• FIFO depth optimizer for Vitis backend by @steltze in #1037
• update sympy version by @marco66colombo in #1214
• Add precisoin bits to recurrent pytorch pytest by @jmitrevs in #1215
• trigger GitLab CI for debugging new CI image by @marco66colombo in #1200
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in #1213
• remove test skip since problem fixed in qonnx by @jmitrevs in #1152
• Unify handling of remove-node when ouput is in outputs by @jmitrevs in #1226
• Remove dependence of profiling tools on torch by @JanFSchulte in #1233

New Contributors

• @jicampos made their first contribution in #1156
• @steltze made their first contribution in #1079
• @marco66colombo made their first contribution in #1214

Full Changelog: v1.0.0...v1.1.0