-
No longer make ExponentPrecisionType and XnorPrecisionType inherit from IntegerPrecisionType 7 of 7 checklist items completed!845 v0.8.0
- Merged
- 8
updated -
Rebased version the PR to add support for ConvTranspose layers 3 of 7 checklist items completed!844 v1.0.0
-
- Merged
- 2
- Approved
updated -
Improve parsing of non-nn.Sequential PyTorch models 6 of 7 checklist items completed!840
- Closed
- 3
updated -
Update dependencies, add testing extras 7 of 7 checklist items completed!837 v0.8.0
- Merged
- 4
updated -
remove obsolete and unused docker directory 7 of 7 checklist items completed!836
- Merged
- 2
updated -
- Merged
- 2
updated -
Add QDepthwiseConv2D, DepthwiseConv2D, DepthwiseConv1D support 8 of 8 checklist items completed!834 v0.8.0
- Merged
- 19
updated -
Fix profiling for GRU/LSTM 3 of 3 checklist items completed!833
- Merged
- 2
updated -
Updated QONNX parsing 8 of 8 checklist items completed!832 v1.0.0
- 1
updated -
- Merged
- 2
updated -
- Merged
- 2
updated -
Fix loading weights in GarNetStacked and GarNet internal array precisions 7 of 7 checklist items completed!827
- Merged
- 3
updated -
Fix loading weights in n-dim dense -> 1x1 conv 7 of 7 checklist items completed!821
- Merged
- 2
updated -
!819
- Closed
updated -
- Merged
- 2
updated -
Fix Vitis Conv1D/2D latency strategy 1 of 1 checklist item completed!815
- Merged
- 3
updated -
Add vcu128 board to VivadoAccelerator backend 4 of 12 checklist items completed!812updated
-
Explicit pointwise Conv1D implementation for "Latency" strategy 6 of 8 checklist items completed!811 v0.8.0
-
hls4ml Optimization API [Part 2] 9 of 9 checklist items completed!809 v1.0.0