hls4ml Files

The major changes compared to v1.1.0 are:

• Added a front end for Keras v3 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1116
• Distributed Arithmetic strategy implementations for Dense, Conv1/2D, and EinsumDense, and HGQ2 suport by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1191
• A PyTorch extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1247
• A new infrastructure for saving/loading hls4ml models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1158
• Support for splitting the model graph into a multi graph to reduce HLS synthesis time by @dimdano in https://github.com/fastmachinelearning/hls4ml/pull/1174
• Bidirectional RNN layer support for Keras frontend and Vitis backend by @enlupi in https://github.com/fastmachinelearning/hls4ml/pull/1310

The full list of changes is:

• Update docs for v1.1.0 by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1234
• update release version in README by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1235
• Fix year/version in README and CITATION.cff by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/1236
• Simple PyTorch extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1247
• Add support for TimeDistributed layer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1177
• Remove calls to remove_node(..., rewire) as the parameter was deprecated by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1250
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1251
• Use unique name for hls4ml layer in pytorch extension api test by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1255
• Fix logic in oneAPI transorm types to not convert a variable twice by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1253
• oneAPI backend update: report by @enlupi in https://github.com/fastmachinelearning/hls4ml/pull/1222
• Fix handling mutiple outputs in onnx by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1263
• docs: Update Quickstart example to use Vitis backend by @nikiburggraf in https://github.com/fastmachinelearning/hls4ml/pull/1258
• Control where TB writes output (stdout, file, or both) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1249
• pyupgrade target version update by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1274
• Add accumulator precision when plotting the model information by @GiuseppeDiGuglielmo in https://github.com/fastmachinelearning/hls4ml/pull/1282
• Add a vertical line for x = 1 = 2^0 in the box plots by @GiuseppeDiGuglielmo in https://github.com/fastmachinelearning/hls4ml/pull/1281
• Fix concat3d when axis=3 /-1 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1285
• Infrastructure for saving/loading hls4ml models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1158
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1301
• Support cloning up to 7 times by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1299
• Keras v3 Support by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1116
• Round inputs for dense unrolled RNN tests to make pytests more stable by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1284
• Change default part to agilex 7, turn of hyper-optimized handshaking, pass clock period by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1304
• Add support for einsum operation to pytorch parser (requires 1116) by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1273
• Fix SeLU lambda precision (Follow-up to [#1287]) by @valerioedu in https://github.com/fastmachinelearning/hls4ml/pull/1298
• Fix parsing einsum with a single input by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1311
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1314
• namespace fix for pointwise conv by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1316
• fix merge templates by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1317
• Support for multi graph build by @dimdano in https://github.com/fastmachinelearning/hls4ml/pull/1174
• template and test fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1319
• Add Cropping layers support by @HamzaEzzRa in https://github.com/fastmachinelearning/hls4ml/pull/1309
• Distributed Arithmetic strategy for Dense, Conv1/2D, and EinsumDense by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1191
• Add support for ConstantPad1d and ConstantPad2d layers in PyTorch con… by @NALozano1 in https://github.com/fastmachinelearning/hls4ml/pull/1322
• Add compatibility with new Vitis command-line compilation flow by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1327
• update namespace pytest, make model weights not be all zeros by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1331
• Report full path when file not found by @llewitt in https://github.com/fastmachinelearning/hls4ml/pull/1325
• Treat PReLU in infer_precision by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1329
• Add (in)equality operators for nnet array by @llewitt in https://github.com/fastmachinelearning/hls4ml/pull/1337
• Initial HGQ support for oneAPI by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1334
• Bidirectional RNN layer support for Keras frontend and Vitis backend by @enlupi in https://github.com/fastmachinelearning/hls4ml/pull/1310
• Io parallel pooling stride fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1335
• relax da4ml version req by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1341
• oneapi backend less copy paste by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1340
• Issue [#184] fix - Propagate options to Vitis HLS by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1342
• remove unnecessary print by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1349
• remove warning print in oneapi report by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1348
• [Docs] Update concepts.rst by @Aditya-138-12 in https://github.com/fastmachinelearning/hls4ml/pull/1351
• Fix missing return statement in time distributed parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1353
• Add LayerNorm support for Vivado by @rianbrooksflynn in https://github.com/fastmachinelearning/hls4ml/pull/1110
• ADD parsing class for rnn layers in keras V3 by @enlupi in https://github.com/fastmachinelearning/hls4ml/pull/1345
• Support for floating point types by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1307
• Fix stream cloning for oneAPI and reshape handling for pytorch by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1354
• Remove ac_float from oneAPI and throw exception if used by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1357
• Purge dim name and distutils by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1321
• Add missing mode flag needed for Vitis 2023.1 by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1350
• setup: Add missing import by @LytixDev in https://github.com/fastmachinelearning/hls4ml/pull/1371
• use int16 instead by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1375
• add linformer parser by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1360
• Fix pytorch related pytest failures by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1377
• lazy import sympy for sr by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1378
• Qonnx binary quant dev by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1355
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1361
• Pooling Template Fix and HGQ2 QPooling Layer Support by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1323
• hgq2 qdense hotfix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1379
• bit exact extension by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1338
• Helpers for CMSSW emulation by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1336
• Automatic type inference for param_t in Parametrised Activations by @nghielme in https://github.com/fastmachinelearning/hls4ml/pull/1139
• Include multigraph doc in index by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1381
• bump da4ml to v0.4 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1386
• rm fxpmath dependency by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1383
• doc update for hgq/da by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1359
• Fix typo in extension documentation by @lkorinek in https://github.com/fastmachinelearning/hls4ml/pull/1389
• Proper Support of Parametrized Activations in Keras V3 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1392
• Avoid layer with name out_something crashing conversion by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1391
• resolve_getitem_source implementation by @rodrigo-breia-lopes in https://github.com/fastmachinelearning/hls4ml/pull/1385
• Allow reshape/transpose after inputs for hgq2 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1368
• Bump checkout version by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1369
• Parallel conv partial fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1380
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1388
• Fix prints in DSP-aware pruning by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1396
• Support for parsing ONNX Pad node by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1352

New Contributors

• @enlupi made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1222
• @nikiburggraf made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1258
• @GiuseppeDiGuglielmo made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1282
• @valerioedu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1298
• @dimdano made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1174
• @HamzaEzzRa made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1309
• @NALozano1 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1322
• @llewitt made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1325
• @Aditya-138-12 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1351
• @rianbrooksflynn made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1110
• @LytixDev made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1371
• @lkorinek made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1389
• @rodrigo-breia-lopes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1385

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v1.1.0...v.1.2.0