Release Notes

iris 1.3.0

Released on 2026-03-20 - GitHub - PyPI

The major changes compared to v1.2.0 are:

• AI Engine (AIE) Backend support as external plugin by @dimdano in https://github.com/fastmachinelearning/hls4ml/pull/1390

• ☢️ Libero backend for rad-hard PolarFire line of FPGAs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1240

• Einsum and EinsumDense for oneAPI by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1424

• vivado/vitis support sample broadcasting merge ops by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1426

• pytest based synthesis tests by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1257

The full list of changes is:

• Bump version to 1.2.0 and switch to ruff for formatting by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1395

• AI Engine (AIE) Backend support as external plugin by @dimdano in https://github.com/fastmachinelearning/hls4ml/pull/1390

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1397

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1399

• Update funding section in README.md by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1403

• Add NGT logo to README by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/1404

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1402

• Manually increment checkout to version v6 by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1405

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1408

• Backend predict hook by @dimdano in https://github.com/fastmachinelearning/hls4ml/pull/1409

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1411

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1414

• pytest based synthesis tests by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1257

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1416

• Remove parametrized fixtures from pytests for pytest 9 compatability by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1417

• Bump upload-artifact version by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1413

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1420

• allow partial config def by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1419

• Add keras3 environment in tests by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1412

• ☢️ Libero backend for rad-hard PolarFire line of FPGAs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1240

• minor fixes to CONTRIBUTING.md by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1423

• Einsum and EinsumDense for oneAPI by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1424

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1425

• Add LHC trigger use case context to README by @siddardhadesu in https://github.com/fastmachinelearning/hls4ml/pull/1418

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1430

• hgq2 homogeneous quant fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1427

• Da custom layer by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1429

• Fix Keras v3 model conversion in numerical profiling by @Abubakar-rashid in https://github.com/fastmachinelearning/hls4ml/pull/1421

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1434

• Uniform test root path by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1435

• Pytest folder naming update by @nghielme in https://github.com/fastmachinelearning/hls4ml/pull/1437

• Fix parsing of activations in Keras v3 non-activation layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1440

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1441

• vivado/vitis support sample broadcasting merge ops by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1426

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1447

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1450

• Bump upload-artifact version by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1449

• fix autoprecision fallback for generic weights by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1453

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/fastmachinelearning/hls4ml/pull/1452

New Contributors

• @siddardhadesu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1418

• @Abubakar-rashid made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1421

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v1.2.0…v1.3.0

hyacinth 1.2.0

Released on 2025-11-03 - GitHub - PyPI

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

gladiolus 1.1.0

Released on 2025-03-17 - GitHub - PyPI

What’s Changed

The major changes compared to v1.0.0 are:

• A new FIFO depth optimizer for the Vitis backend by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1037

• Expansion of the oneAPI backend by adding depthwise convolution and RNN State and Activation Quantizers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1131 and https://github.com/fastmachinelearning/hls4ml/pull/1195

• A new general transpose implementation for vivado/vitis by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1124, adapted for oneAPI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1165

• New depthwise 1D and 2D implementations for the resource strategy for io_stream by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1079

The full list of changes is:

• Don’t overwrite already set accum_t, fix pointwise output resolution by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1146

• Split hgq tests and isolate qkeras tests to make tests run in under 1h by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1153

• Depthwise convolution for oneAPI by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1131

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1159

• Fix Vivado Accelerator missing partition factor variable by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1160

• Bug fixes for channel-last conversions in pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1161

• Support Constant nodes in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1123

• oneAPI 2025.0 include changes by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1149

• Update Torch profiler by @jicampos in https://github.com/fastmachinelearning/hls4ml/pull/1156

• Add general transpose for vivado/vitis by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1124

• remove np.float_ (deprecated in numpy>=2.0) by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1172

• add check for no inputs in insert_node by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1170

• added check for conv implementation by @jicampos in https://github.com/fastmachinelearning/hls4ml/pull/1155

• Lazy converter imports and migrate to pyproject.toml by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1094

• Fix pytorch upsample parsing by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1186

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1182

• Fixes for quantised RNNs in data type inconsistencies by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1171

• Support multiple outputs in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1151

• general transpose for oneAPI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1165

• add option to not write tar.gz for oneAPI and Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1189

• Fix paths to weights in build_lib.sh for VivadoAccelator backend by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1198

• Fix link to FAQ in README.md by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1201

• Update pull request template by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1202

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1199

• oneAPI RNN State and Activation Quantizers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1195

• put code_gen.h in custom namespace by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1104

• Fix typo in pyproject.toml by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1204

• Adjust model output if last node is removed by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1205

• remove old variables when moving of scales by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1206

• Initial values for the hidden/cell state for LSTM and GRU models in Pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1120

• Depthwise 1D and 2D Resource strategy for io_stream by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1079

• make test_activations less sensitive to random seed values by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1211

• FIFO depth optimizer for Vitis backend by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1037

• update sympy version by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1214

• Add precisoin bits to recurrent pytorch pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1215

• trigger GitLab CI for debugging new CI image by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1200

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1213

• remove test skip since problem fixed in qonnx by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1152

• Unify handling of remove-node when ouput is in outputs by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1226

• Remove dependence of profiling tools on torch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1233

New Contributors

• @jicampos made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1156

• @steltze made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1079

• @marco66colombo made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1214

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v1.0.0…v1.1.0

foxglove 1.0.0

Released on 2024-12-09 - GitHub - PyPI

What’s Changed

hls4ml v1.0.0 “foxglove” introduces several significant improvements:

• A new QONNX frontend by @jmitrevs introduced in https://github.com/fastmachinelearning/hls4ml/pull/979

• The ability for hls4ml to automatically infer the precision of data types by @vloncar introduced in https://github.com/fastmachinelearning/hls4ml/pull/855

• The addition of an experimental backend for Intel oneAPI by @jmitrevs introduced in https://github.com/fastmachinelearning/hls4ml/pull/955

• The addition of a backend for Siemens Catapult by @dgburnette in https://github.com/fastmachinelearning/hls4ml/pull/956

• Added support for HGQ proxy models by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/914

• An API for hardware-aware optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/768 and https://github.com/fastmachinelearning/hls4ml/pull/809

The full list of other improvements and fixes is:

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/949

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/953

• hls4ml Optimization API [Part 1] by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/768

• QKeras support for RNN layers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/856

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/962

• Try to fix sphinx problem by restricting tensorflow-model-optimization by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/967

• Bump pre-commit/action from 3.0.0 to 3.0.1 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/968

• Change fractional (and others) to be a property, move quantizers by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/964

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/969

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/971

• vitis backend tarball fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/972

• remove special vitis version of nnet_dense_resource.h by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/975

• Allow Vitis synthesis tests by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/927

• Fix cleanup of synthesis tests (leftover from 927) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/989

• Fix sphinx by pinning tensorflow<=2.15 by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/992

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/984

• add clock uncertainty configuration option by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/870

• Stage initial set of changes for the Catapult backend by @dgburnette in https://github.com/fastmachinelearning/hls4ml/pull/956

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/999

• fix unwanted tested file change in #956 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1000

• Fix SR backend synth missing variables by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/993

• Upsampling support for PyTorch models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/977

• Split fpga_types into separate files by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/998

• Support negative_slope in quantized_relu by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/987

• Group more tests per YAML to reduce the number of envs created by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/996

• Automatic precision inference by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/855

• Remove unnecessary transposes related to conversion to channels_last format by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/976

• Update pytest docker image to 0.5.4 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1005

• Fix pre-commit warning and change ‘.h5’ to ‘.keras’ for written output by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1006

• Fix extension test for Keras v3 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1009

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1007

• updated pytest docker image by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1017

• SepConv1d/2d for io_parallel with Latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1012

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1021

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1023

• Latency Pooling Header Updates by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/973

• Make im2col default option for quartus by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1010

• add protection for when kernel_quantizer is None by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/997

• prevent test directory overwrites for activation by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1031

• Update Jenkinsfile to use new Docker image and Python 3.10 environment by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1033

• clean-up test ci yaml generater by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1036

• Add View to layer name map for pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1039

• Add RNN support for Pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/850

• Add Vitis to pytorch API tests by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1040

• clean up mult-dimensional dense by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1042

• Add namespaces and optional writer config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/986

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1044

• Add support for HGQ proxy model by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/914

• Bug Fix for Operand Shape Mismatch in BatchNorm Fusion (PyTorch) by @sei-rquartiano in https://github.com/fastmachinelearning/hls4ml/pull/1045

• remove precision settings that make pytest for batchnorm in pytorch fail by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1053

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1047

• rm slow mnist training in test by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1018

• Add an optimizer to replace SeparableConv by Depthwise + Conv (pointwise) by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1022

• Add functionality to use granularity option also for pytorch models by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1051

• Update pooling logic for Vivado, Vitis, and Catapult backends by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1056

• remove padding attribute by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1061

• Run long-running pytests out of the batch by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1062

• Fix tanh activiation in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1055

• make auto the default for layer config by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1016

• remove checks on ‘padding’ that were missed in previous PR by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1064

• Remove extras flow by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1067

• Expose alpha and theta type for parametrized activations by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1069

• Raise exception on compile errors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1068

• update qkeras in Jenkinsfile by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1072

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1075

• hls4ml Optimization API [Part 2] by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/809

• Hardcore weight txt path by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1089

• quote the ${WEIGHT_DIR} to handle special characters by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1091

• Beginnings of the oneAPI backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/955

• update keras activation parsing, especially leaky relu by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1085

• Fix softmax parsing in pytorch and add test by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1086

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1098

• Change indexing in filling result for io_parallel convolutions, Vitis by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1102

• Update QONNX parsing for 1.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/979

• remove incorrect input from Constant nodes by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1119

• add max_precision to onnx parser by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1113

• Add RF to config templates for “Merge” layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1121

• Add doc for HGQ by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1117

• Multi output fix 2 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1103

• Make auto default precision for pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1112

• remove incorrect setting of result_t by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1130

• Fix problem with scale being a multidimensional array. by @jurevreca12 in https://github.com/fastmachinelearning/hls4ml/pull/1132

• Added support for QONNX Resize node ingestion and tested with tiny UNet model by @nghielme in https://github.com/fastmachinelearning/hls4ml/pull/1122

• Update install_requires for 1.0.0 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1136

• Pointwise Conv1D with code generation for “Latency” strategy (update of #811) by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/881

• Introduce optional description to layer attributes by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1127

• Qonnx warnings by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1142

• Fixes to parsing of pytorch models when using torch functionals by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1143

• Update README.md for v1.0.0 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1100

• Temporary workaround for QKeras installation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1145

New Contributors

• @laurilaatu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/856

• @dgburnette made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/956

• @sei-rquartiano made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1045

• @jurevreca12 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1132

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.8.1…v1.0.0

edelweiss 0.8.1

Released on 2023-12-19 - GitHub - PyPI

What’s Changed

• Fix for #905 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/906

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/921

• Fix logos in README.md by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/930

• Fix writer precision when fp bits >= 14 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/909

• Let repack_stream optimizer inheirt original precision by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/907

• Update A3D3 grant no. by @schsu in https://github.com/fastmachinelearning/hls4ml/pull/941

• Add precision inherition for when generating stream clone by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/911

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/942

• Quartus multi out with stream fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/908

• Fix profiling for Keras LSTM layers. by @Landay7 in https://github.com/fastmachinelearning/hls4ml/pull/940

• Fix for multiple inputs that may get out of order by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/937

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/944

• Bump actions/upload-artifact from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/943

• better repalce_node fn by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/934

• bump to 0.8.1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/945

New Contributors

• @schsu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/941

• @Landay7 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/940

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.8.0…v0.8.1

edelweiss 0.8.0

Released on 2023-11-16 - GitHub - PyPI

What’s Changed

• Decouple pipeline style from strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/781

• Don’t use reader in ModelGraph and layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/770

• Remove tf_to_hls by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/795

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/796

• Fix parsing of QConv2DBatchnorm weights by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/802

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/801

• Discussion - Inlined Conv slows down latency significantly (up to x15 - x20) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/800

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/807

• Fix over-allocation of bits for quantised po2 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/806

• Propagate zeros from Conv layers to multiplication config by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/797

• Fix Vitis Conv1D/2D latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/815

• Improved parsing of pytorch models using torch.FX - Clean by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/799

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/816

• Support for parsing nested models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/794

• Fix loading weights in n-dim dense -> 1x1 conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/821

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/828

• Fix loading weights in GarNetStacked and GarNet internal array precisions by @joshlerner in https://github.com/fastmachinelearning/hls4ml/pull/827

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/830

• Fix profiling for GRU/LSTM by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/833

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/835

• remove obsolete and unused docker directory by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/836

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/842

• Remove obsolete parameter mapping between pytorch and keras by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/847

• Make binary CNN match between Keras and hls4ml by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/804

• No longer make ExponentPrecisionType and XnorPrecisionType inherit from IntegerPrecisionType by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/845

• Add support for flattening to the pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/852

• Add option to configure IP version by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/851

• Bug fix for named nn.Sequential in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/848

• Add QDepthwiseConv2D, DepthwiseConv2D, DepthwiseConv1D support by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/834

• Symbolic expressions in hls4ml by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/660

• Update dependencies, add testing extras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/837

• Bump actions/checkout from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/866

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/869

• try to use new runners for gitlab CI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/879

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/880

• Fix weight precision format string by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/877

• add acknowledgments by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/862

• Support for quantized SeparableConv1D/2D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/861

• Speed up Keras profiling by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/863

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/882

• Fix profiling SeparableConv1D and SeparableConv2D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/891

• Add support for filt_height==1 for streaming quartus conv2d by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/886

• Fix config structure name in pragma for SeparableConv1D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/884

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/895

• Fix bit overflow with softmax by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/887

• bump 0.8.0rc1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/915

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/902

• Add funding acknowledgements by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/918

• Fix fetching models from example-models repo by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/919

• add blank line to make rst format correct by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/923

• Update default FPGA part number from KU115 to VU13P by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/924

• update to 0.8.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/925

New Contributors

• @pre-commit-ci made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/796

• @joshlerner made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/827

• @qberthet made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/891

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.1…v0.8.0

edelweiss 0.8.0rc1

Released on 2023-11-08 - GitHub - PyPI

What’s Changed

• Decouple pipeline style from strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/781

• Don’t use reader in ModelGraph and layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/770

• Remove tf_to_hls by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/795

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/796

• Fix parsing of QConv2DBatchnorm weights by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/802

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/801

• Discussion - Inlined Conv slows down latency significantly (up to x15 - x20) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/800

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/807

• Fix over-allocation of bits for quantised po2 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/806

• Propagate zeros from Conv layers to multiplication config by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/797

• Fix Vitis Conv1D/2D latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/815

• Improved parsing of pytorch models using torch.FX - Clean by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/799

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/816

• Support for parsing nested models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/794

• Fix loading weights in n-dim dense -> 1x1 conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/821

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/828

• Fix loading weights in GarNetStacked and GarNet internal array precisions by @joshlerner in https://github.com/fastmachinelearning/hls4ml/pull/827

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/830

• Fix profiling for GRU/LSTM by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/833

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/835

• remove obsolete and unused docker directory by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/836

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/842

• Remove obsolete parameter mapping between pytorch and keras by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/847

• Make binary CNN match between Keras and hls4ml by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/804

• No longer make ExponentPrecisionType and XnorPrecisionType inherit from IntegerPrecisionType by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/845

• Add support for flattening to the pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/852

• Add option to configure IP version by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/851

• Bug fix for named nn.Sequential in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/848

• Add QDepthwiseConv2D, DepthwiseConv2D, DepthwiseConv1D support by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/834

• Symbolic expressions in hls4ml by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/660

• Update dependencies, add testing extras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/837

• Bump actions/checkout from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/866

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/869

• try to use new runners for gitlab CI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/879

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/880

• Fix weight precision format string by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/877

• add acknowledgments by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/862

• Support for quantized SeparableConv1D/2D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/861

• Speed up Keras profiling by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/863

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/882

• Fix profiling SeparableConv1D and SeparableConv2D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/891

• Add support for filt_height==1 for streaming quartus conv2d by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/886

• Fix config structure name in pragma for SeparableConv1D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/884

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/895

• Fix bit overflow with softmax by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/887

• bump 0.8.0rc1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/915

New Contributors

• @pre-commit-ci made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/796

• @joshlerner made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/827

• @qberthet made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/891

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.1…v0.8.0rc1

delphinium 0.7.1

Released on 2023-05-13 - GitHub - PyPI

What’s Changed

• bump version to v0.7.0 by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/778

• Fix for 2D conv layers in the special case of io_parallel with full parallelization by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/760

• Fix RNN layers when strategy=resource by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/780

• Update Jenkins test environment to avoid dependency hell by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/786

• Explicitly set strategy for pointwise conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/785

• Minor docs fixes for 0.7.1 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/788

• bump 0.7.1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/791

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.0…v0.7.1

0.7.0: delphinium

Released on 2023-04-26 - GitHub - PyPI

What’s Changed

• fix conv1d io_parallel resource by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/403

• Speed up CI tests by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/407

• Fix GlobalPooling1D Layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/399

• Fix batched multiple inputs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/414

• Fixed ‘qkeras_mnist_dense’ example build problem #423 by @siorpaes in https://github.com/fastmachinelearning/hls4ml/pull/424

• Update for pyyaml 6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/435

• axi_stream_driver update by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/420

• Reshape fixes: don’t repack stream for flatten; remove final reshape by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/443

• Fix Conv2D with io_type = io_parallel & Strategy: Resource by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/448

• Support applying Softmax over multidimensional tensors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/384

• Disable some unsupported layers by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/447

• Fixes: quantized_relu & unsigned profiling part II by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/441

• GarNet and GarNetStack in config.py by @yiiyama in https://github.com/fastmachinelearning/hls4ml/pull/344

• support ZeroPadding layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/480

• New backend development framework by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/395

• Register ApplyAlpha layer templates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/499

• Parsing extended by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/501

• Remove intermediate casting in product by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/490

• Add QKeras as a package dependency by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/511

• Copy flows from config by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/510

• VivadoAccelerator backend updates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/508

• Optimized look-up table by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/527

• Upsampling2D test case by @ChiRuiChen in https://github.com/fastmachinelearning/hls4ml/pull/520

• Support UpSampling1D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/475

• RNN support (part 1) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/521

• Quartus Custom Matrix Multiplication & Quantization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/523

• Vivado-equivalent implementation of Softmax on Quartus by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/540

• Ensure 2 bits for scale in po2 quantizers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/531

• Link update by @bkmgit in https://github.com/fastmachinelearning/hls4ml/pull/519

• Fix removal of nodes ingested by multiple downstream nodes by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/544

• Enable SeparableConv2d by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/547

• Extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/528

• change string ReuseFactor to int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/416

• Make the size of bn scale and bias what they really are by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/532

• Raise runtime error when a layer is named input by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/482

• fix insertion before a node with multiple inputs + support additional broadcasting by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/551

• Pointwise conv1d/2d resource by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/471

• Quartus Embedding Layer by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/548

• Fix for QActivations passed as an argument by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/553

• Don’t override precision directly in the QKeras optimizer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/567

• Remove the in/out size from top function by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/559

• Transpose2d, Concatenate2d, and up to 3 Clones for io_stream by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/402

• Remove io_serial as io_stream and add some more info in docs. by @Duchstf in https://github.com/fastmachinelearning/hls4ml/pull/334

• Update docs for v0.6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/453

• Use correct number of args for multiple outputs by @apfusco in https://github.com/fastmachinelearning/hls4ml/pull/487

• Fixed a few typos in the documentation by @pitmonticone in https://github.com/fastmachinelearning/hls4ml/pull/467

• returning integer from _compute_n_samples by @JochiSt in https://github.com/fastmachinelearning/hls4ml/pull/537

• Providing support for Alveo boards by @selwyn96 in https://github.com/fastmachinelearning/hls4ml/pull/552

• Make layer names case sensitive in config. by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/577

• Add issue and PR templates by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/582

• Vivado Backend GRU/LSTM support by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/560

• Update CI template syntax by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/593

• Update flow dependencies by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/588

• Fix parsing of ZeroPadding layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/595

• remove cppname by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/562

• Remove email helpline from the docs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/601

• Fixes for GRU/LSTM in Vivado backend by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/598

• Remove io_serial by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/609

• Fix test_graph by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/611

• Override parent backend optimizer passes with derived backend passes by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/597

• Enforce function pipelining when using io_parallel with Resource strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/605

• FIFO depth optimization by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/509

• Add tracing support for the quartus backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/583

• Quartus streaming support for Activations, Dense & Batch Normalization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/557

• QConv alpha != 1 bug fix by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/612

• Quartus Stream Embedding by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/625

• change master to main by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/602

• Edit order of the optimizers in the flow so that BramFactor is followed by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/621

• Softmax LUT Optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/570

• Quartus Synthesis Flow Improvement by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/618

• Quartus Extensions by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/628

• Quartus GRU by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/596

• Quartus Merge layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/634

• fix nondefault project name handling by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/626

• Fix parsing of logic synthesis reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/639

• Fix conv1d stream implementation hls directives by @Jonathan-Shoemaker in https://github.com/fastmachinelearning/hls4ml/pull/635

• Implementation and optimizations linked to Simple-RNN and LSTM for qu… by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/575

• Softsign optimization by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/585

• Parallel CNNs, Pooling & Image Layers for Quartus Backend by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/561

• Quartus Streaming Softsign (PR #585 contd.) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/655

• Remove final reshapes even for Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/661

• Unrolled CNN implementation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/600

• the strategy was not propagated in the pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/663

• Fix keras model loading issue with loading model with KerasH5 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/664

• append applied_flows container before filling instead of after by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/641

• set version using setuptools_scm by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/479

• Argmax Softmax by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/627

• Fix version extraction in Sphinx config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/669

• Add requested citations to README by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/615

• skip BatchNorm fusion when input/output is used multiple times by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/481

• Use wider accum_t for (average) pooling by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/681

• Quartus Streaming Conv, Pooling & Image layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/656

• Create branch on PR by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/636

• Delete example-prjs directory by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/682

• Adiabatically turn on pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/678

• Add causal padding by @cgutsche in https://github.com/fastmachinelearning/hls4ml/pull/688

• Update pre-commit GitHub Action by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/689

• New config_from_keras_model by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/690

• remove obsolete np.int and np.float by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/703

• Update p-clang-format to work on mac by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/704

• Fix function call in Alveo tcl script by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/694

• add readme for contrib by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/706

• WIP Add custom KL loss layer HLS implementation by @katyagovorkova in https://github.com/fastmachinelearning/hls4ml/pull/606

• Fix incorrectly linted build() command by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/709

• For encoded convolution, add check for when min_width would have been larger than in_width by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/610

• fifo_depth_optimization flow require ip, not writer, before running by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/642

• update isort to fix pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/719

• Fixed sign parsing for ac_fixed and ac_int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/727

• Correctly expand dims of pointwise layer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/715

• Support keepdims in GlobalPooling layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/716

• Register layer attributes in VivadoAccelerator backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/724

• Add quantized sigmoid, fix quantized tanh for QKeras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/569

• print_vivado_report function for nicer reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/730

• Quartus bram factor by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/700

• Fix inplace variables by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/714

• Fix for cloned stream that is subsequently flattened by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/708

• Vitis HLS backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/629

• Update documentation for v0.7.0 release by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/710

• Fix release notes + version in docs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/742

• Fix precommits by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/741

• mv dependabot.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/743

• Bump actions/setup-python from 2 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/748

• fix Vitis pragmas messed up by pre-commit by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/751

• Additional cleanup of the codebase by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/750

• Fix for BatchNormalization layers with center=False or scale=False by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/754

• Remove references to GPL since we now use a different license by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/761

• Fix pooling layers when padding is applied from the left/top by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/757

• Further update documentation for 0.7.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/744

• Update pypi-publish.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/763

• Fix pypi version by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/766

• add a default weight_size by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/772

• CNNs with binary inputs and weights need fixes by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/749

• Minor documentation updates by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/774

New Contributors

• @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424

• @nemerchiedde made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/527

• @ChiRuiChen made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/520

• @bo3z made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/523

• @bkmgit made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/519

• @apfusco made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/487

• @pitmonticone made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/467

• @JochiSt made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/537

• @selwyn96 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/552

• @Jonathan-Shoemaker made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/635

• @calad0i made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/664

• @cgutsche made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/688

• @dependabot made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/748

• @JanFSchulte made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/757

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.6.0…v0.7.0

0.7.0rc1: delphinium rc1

Released on 2023-04-15 - GitHub - PyPI

What’s Changed

• fix conv1d io_parallel resource by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/403

• Speed up CI tests by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/407

• Fix GlobalPooling1D Layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/399

• Fix batched multiple inputs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/414

• Fixed ‘qkeras_mnist_dense’ example build problem #423 by @siorpaes in https://github.com/fastmachinelearning/hls4ml/pull/424

• Update for pyyaml 6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/435

• axi_stream_driver update by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/420

• Reshape fixes: don’t repack stream for flatten; remove final reshape by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/443

• Fix Conv2D with io_type = io_parallel & Strategy: Resource by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/448

• Support applying Softmax over multidimensional tensors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/384

• Disable some unsupported layers by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/447

• Fixes: quantized_relu & unsigned profiling part II by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/441

• GarNet and GarNetStack in config.py by @yiiyama in https://github.com/fastmachinelearning/hls4ml/pull/344

• support ZeroPadding layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/480

• New backend development framework by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/395

• Register ApplyAlpha layer templates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/499

• Parsing extended by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/501

• Remove intermediate casting in product by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/490

• Add QKeras as a package dependency by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/511

• Copy flows from config by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/510

• VivadoAccelerator backend updates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/508

• Optimized look-up table by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/527

• Upsampling2D test case by @ChiRuiChen in https://github.com/fastmachinelearning/hls4ml/pull/520

• Support UpSampling1D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/475

• RNN support (part 1) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/521

• Quartus Custom Matrix Multiplication & Quantization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/523

• Vivado-equivalent implementation of Softmax on Quartus by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/540

• Ensure 2 bits for scale in po2 quantizers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/531

• Link update by @bkmgit in https://github.com/fastmachinelearning/hls4ml/pull/519

• Fix removal of nodes ingested by multiple downstream nodes by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/544

• Enable SeparableConv2d by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/547

• Extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/528

• change string ReuseFactor to int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/416

• Make the size of bn scale and bias what they really are by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/532

• Raise runtime error when a layer is named input by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/482

• fix insertion before a node with multiple inputs + support additional broadcasting by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/551

• Pointwise conv1d/2d resource by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/471

• Quartus Embedding Layer by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/548

• Fix for QActivations passed as an argument by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/553

• Don’t override precision directly in the QKeras optimizer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/567

• Remove the in/out size from top function by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/559

• Transpose2d, Concatenate2d, and up to 3 Clones for io_stream by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/402

• Remove io_serial as io_stream and add some more info in docs. by @Duchstf in https://github.com/fastmachinelearning/hls4ml/pull/334

• Update docs for v0.6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/453

• Use correct number of args for multiple outputs by @apfusco in https://github.com/fastmachinelearning/hls4ml/pull/487

• Fixed a few typos in the documentation by @pitmonticone in https://github.com/fastmachinelearning/hls4ml/pull/467

• returning integer from _compute_n_samples by @JochiSt in https://github.com/fastmachinelearning/hls4ml/pull/537

• Providing support for Alveo boards by @selwyn96 in https://github.com/fastmachinelearning/hls4ml/pull/552

• Make layer names case sensitive in config. by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/577

• Add issue and PR templates by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/582

• Vivado Backend GRU/LSTM support by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/560

• Update CI template syntax by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/593

• Update flow dependencies by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/588

• Fix parsing of ZeroPadding layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/595

• remove cppname by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/562

• Remove email helpline from the docs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/601

• Fixes for GRU/LSTM in Vivado backend by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/598

• Remove io_serial by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/609

• Fix test_graph by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/611

• Override parent backend optimizer passes with derived backend passes by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/597

• Enforce function pipelining when using io_parallel with Resource strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/605

• FIFO depth optimization by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/509

• Add tracing support for the quartus backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/583

• Quartus streaming support for Activations, Dense & Batch Normalization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/557

• QConv alpha != 1 bug fix by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/612

• Quartus Stream Embedding by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/625

• change master to main by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/602

• Edit order of the optimizers in the flow so that BramFactor is followed by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/621

• Softmax LUT Optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/570

• Quartus Synthesis Flow Improvement by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/618

• Quartus Extensions by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/628

• Quartus GRU by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/596

• Quartus Merge layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/634

• fix nondefault project name handling by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/626

• Fix parsing of logic synthesis reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/639

• Fix conv1d stream implementation hls directives by @Jonathan-Shoemaker in https://github.com/fastmachinelearning/hls4ml/pull/635

• Implementation and optimizations linked to Simple-RNN and LSTM for qu… by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/575

• Softsign optimization by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/585

• Parallel CNNs, Pooling & Image Layers for Quartus Backend by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/561

• Quartus Streaming Softsign (PR #585 contd.) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/655

• Remove final reshapes even for Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/661

• Unrolled CNN implementation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/600

• the strategy was not propagated in the pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/663

• Fix keras model loading issue with loading model with KerasH5 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/664

• append applied_flows container before filling instead of after by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/641

• set version using setuptools_scm by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/479

• Argmax Softmax by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/627

• Fix version extraction in Sphinx config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/669

• Add requested citations to README by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/615

• skip BatchNorm fusion when input/output is used multiple times by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/481

• Use wider accum_t for (average) pooling by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/681

• Quartus Streaming Conv, Pooling & Image layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/656

• Create branch on PR by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/636

• Delete example-prjs directory by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/682

• Adiabatically turn on pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/678

• Add causal padding by @cgutsche in https://github.com/fastmachinelearning/hls4ml/pull/688

• Update pre-commit GitHub Action by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/689

• New config_from_keras_model by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/690

• remove obsolete np.int and np.float by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/703

• Update p-clang-format to work on mac by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/704

• Fix function call in Alveo tcl script by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/694

• add readme for contrib by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/706

• WIP Add custom KL loss layer HLS implementation by @katyagovorkova in https://github.com/fastmachinelearning/hls4ml/pull/606

• Fix incorrectly linted build() command by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/709

• For encoded convolution, add check for when min_width would have been larger than in_width by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/610

• fifo_depth_optimization flow require ip, not writer, before running by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/642

• update isort to fix pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/719

• Fixed sign parsing for ac_fixed and ac_int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/727

• Correctly expand dims of pointwise layer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/715

• Support keepdims in GlobalPooling layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/716

• Register layer attributes in VivadoAccelerator backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/724

• Add quantized sigmoid, fix quantized tanh for QKeras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/569

• print_vivado_report function for nicer reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/730

• Quartus bram factor by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/700

• Fix inplace variables by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/714

• Fix for cloned stream that is subsequently flattened by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/708

• Vitis HLS backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/629

• Update documentation for v0.7.0 release by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/710

• Fix release notes + version in docs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/742

• Fix precommits by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/741

• mv dependabot.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/743

• Bump actions/setup-python from 2 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/748

• fix Vitis pragmas messed up by pre-commit by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/751

• Additional cleanup of the codebase by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/750

• Fix for BatchNormalization layers with center=False or scale=False by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/754

• Remove references to GPL since we now use a different license by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/761

• Fix pooling layers when padding is applied from the left/top by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/757

• Further update documentation for 0.7.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/744

• Update pypi-publish.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/763

• Fix pypi version by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/766

New Contributors

• @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424

• @nemerchiedde made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/527

• @ChiRuiChen made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/520

• @bo3z made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/523

• @bkmgit made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/519

• @apfusco made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/487

• @pitmonticone made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/467

• @JochiSt made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/537

• @selwyn96 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/552

• @Jonathan-Shoemaker made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/635

• @calad0i made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/664

• @cgutsche made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/688

• @dependabot made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/748

• @JanFSchulte made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/757

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.6.0…v0.7.0rc1

0.6.0: coris

Released on 2021-11-12 - GitHub - PyPI

What’s Changed

• VivadoAccelerator backend: target pynq-z2 and zcu102 boards directly from hls4ml by @nicologhielmetti

• Updated PyTorch and ONNX converters by @Duchstf

• line_buffer Conv2D implementation for io_stream: reduced resource usage and latency by @Keb-L, @violatingcp, @vloncar

• Support QConv2DBatchnorm layer from QKeras by @nicologhielmetti

• Improved profiling plots - easier to compare original vs hls4ml converted models by @maksgraczyk

• Better derivation of data types for QKeras models by @jmduarte, @thesps

• Improved CI by @thesps

• More support for models with branches, skip connections, Merge and Concatenate layers by @jmduarte, @vloncar

• Support for Dense layers over multi-dimensional tensors by @vloncar

• Overall improvements by @vloncar, @jmduarte, @thesps, @jmitrevs & others

New Contributors

• @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424

• @jmitrevs made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/403

• @anders-wind made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/302

• @KOVI89alipes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/318

• @maksgraczyk made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/323

• @Keb-L made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/332

• @ConsVin made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/307

• @nicologhielmetti made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/298

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.5.0…v0.6.0

0.5.0: bartsia

Released on 2021-03-05 - GitHub - PyPI

What’s new:

• Streaming IO layer implementations, especially of Convolutional layers, accessed through the config with IOType: io_stream. Scales CNN support to much larger models than previously possible (see arXiv:2101.05108)

• New documentation and API reference

• Further optimizations for QKeras / quantization aware training. A ‘shift’ operation is now used for po2 quantizers

• Allow redefinition of weights directory for standalone project compilation

• profiling for PyTorch models

Deprecated:

• IOType : io_serial is deprecated, and superceded by new IOType: io_stream

Bugfixes:

• Fix to Initiation Interval and different min/max latency for Strategy: Resource

• Fix warnings in hls4ml command line script flow

• Write yml config from Python API - for mixed API / command line flow

0.5.0-beta

Released on 2021-01-18 - GitHub - PyPI

Pre-release of hls4ml version v0.5.0.

What’s new:

• Streaming IO layer implementations, especially of Convolutional layers, accessed through the config with io_type: io_stream. Scales CNN support to much larger models than previously possible (see paper)

• New documentation and API reference

• Further optimizations for QKeras / quantization aware training. A ‘shift’ operation is now used for po2 quantizers

• Allow redefinition of weights directory for standalone project compilation

0.4.0: aster

Released on 2020-10-30 - GitHub - PyPI

What’s new:

• Support for GarNet layer (see paper)

• Input layer precision added to config generator utility

• New ‘SkipOptimizers’ config option. Now you can run all Optimizers by default (as in v0.3.0) but subtract any specified by ‘SkipOptimizers’ e.g. hls_config['SkipOptimizers'] = ['fuse_consecutive_batch_normalization']

• Print out the latency report from Cosimulation

Bugfixes:

• Fixes related to tensorflow 2.3: new Functional API, changes to handling of Input layer

• Fix error with config generator utility and activation layers gor granularity='name'

• Fix issue with reloading of emulation library after configuration change

• Fix to handling of layers with use_bias=False and merged Dense and BatchNormalization

v0.3.0

Released on 2020-07-31 - GitHub - PyPI

What’s new:

• API expansion:

  • Create configuration dictionary from model object

  • Run ‘C Simulation’ from Python with hls_model.predict(X)

  • Trace model layer output with hls_model.trace(X)

  • Write HLS project, run synthesis flow from Python

• QKeras support: convert models trained using layers and quantizers from QKeras

• Example models moved to separate repo, added as a submodule with an API to retrieve them

• New Softmax implementations

• Minor fixes: weights exported at higher precision, concatenate layer shape corrected

v0.2.0

Released on 2020-03-31 - GitHub - PyPI

What’s new:

• tf_to_hls: convert tensorflow protobuf (.pb) models to HLS projects

• Support for Keras model .h5 files (extending existing support for .json architecture + .h5 weights format)

• Support larger Conv1D / 2D layers

• Support for binary and ternary layers from QKeras

• API enhancements for addition of custom layer and new backends

• Keras and HLS model profiling tool

• hls4ml report command to gather HLS build reports

• hls4ml build -l command to run logic synthesis

• Fused Batch Normalization and Dense layer optimization pass

v0.1.6

Released on 2020-02-10 - GitHub - PyPI

• Support for larger Dense layers (enabled with Strategy: Resource in the configuration file)

• Binary/Ternary NN refinements

• Built-in optimization framework

• Optional C/RTL validation

v0.1.5

Released on 2019-08-02 - GitHub - PyPI

v0.1.2

Released on 2018-03-20 - GitHub - PyPI

Update license

v0.1.1

Released on 2018-03-16 - GitHub - PyPI

second beta version: fixed README