- 1cdc467 Added a lower bound for the valid range of shift by Jacob Bohlin · 4 years ago
- 6c87807 MLBEDSW-2664 Clarify help for CLI-opt permanent-storage by Patrik Gustavsson · 4 years ago
- 9baa4c3 MLBEDSW-2822 Account for NHCWB16 in scheduler est. by Patrik Gustavsson · 4 years ago
- f899231 MLBEDSW-2611: Update global scale for 16 bit to tanh and sigmoid by Charles Xu · 4 years ago
- bb1b09e MLBEDSW-2783 Vela crashed on empty tflite file by Michael McGeagh · 4 years ago
- a3aad93 MLBEDSW-2824: Add mapping for ROUND operator by Dwight Lidman · 4 years ago
- b16dcce vela: Minor refactor of operation class by Tim Hall · 4 years, 1 month ago
- e5b0163 MLBEDSW-2683: Neural Network MACs is wrong by Tim Hall · 4 years, 1 month ago
- fb85873 MLBEDSW-2728: Only insert primary op for NPU ops by Jacob Bohlin · 4 years ago
- d2a972d MLBEDSW-2731: Allow all TensorFlow Lite operators to pass through by Dwight Lidman · 4 years ago
- 2573311 MLBEDSW-2729: Add restrictions for shapeless tensors by Dwight Lidman · 4 years ago
- fa34c6f MLBEDSW-2636 Prevent DMA of weight to Sram in some cases by Patrik Gustavsson · 4 years ago
- eebb1c2 MLBEDSW-2779 Avoid NHCWB16 in some SplitSliceRead cases by Patrik Gustavsson · 4 years ago
- 597fd3f [MLBEDSW-2657] Softmax uint8/int8 by Fredrik Svedberg · 4 years ago
- 30cb47a MLBEDSW-2718: Fix a bug that would reshape TransposeConv input by Jacob Bohlin · 4 years ago
- 940fdee MLBEDSW-2589: Skip weight compression for CPU ops by Dwight Lidman · 4 years ago
- 29d568e MLBEDSW-2779 Consider num dimensions, in check for NHCWB16 by Patrik Gustavsson · 4 years ago
- 289a41d Vela: Rework NPU/DMA dependency insertion (for MLBEDSW-2620) by Tim Hall · 4 years, 1 month ago
- f767b93 MLBEDSW-2732: Added complex64 to datatypes by Jacob Bohlin · 4 years ago
- 0b8268a MLBEDSW-2688: Improved LUT support by Louis Verhaard · 4 years, 1 month ago
- 458a208 MLBEDSW-2570 Avoid usage of NHCWB16 for some cases by Patrik Gustavsson · 4 years ago
- be733cf MLBEDSW-2639: Remove reverse_op_order attribute by Jacob Bohlin · 4 years ago
- bf61268 MLBEDSW-2755: Added check that ifm2_tensor is set by Jacob Bohlin · 4 years ago
- 8b24f2b [MLBEDSW-2749] removed the decorator for typecheck by Manupa Karunaratne · 4 years ago
- 1a9d20e MLBEDSW-2726: Vela crashes when marking tensor with TensorPurpose.Unknown by Dwight Lidman · 4 years ago
- 7ad408b MLBEDSW-2586: Null check before accessing tensor resampling mode by Dwight Lidman · 4 years ago
- c0bb899 MLBEDSW-2696 Fix Sram exceeded for Sram spilling by Patrik Gustavsson · 4 years ago
- 89a6bbf MLBEDSW-2681: Ceiling the upscale for OFM/IFM by Charles Xu · 4 years ago
- de2a57f MLBEDSW-2684: Fix weight compression scale calculations for FC by Jacob Bohlin · 4 years ago
- 8d3216f vela: Remove redundant import, reuse existing func by Michael McGeagh · 4 years ago
- c5b549b MLBEDSW-2637 Utilise new tensor and operator funcs by Michael McGeagh · 4 years, 1 month ago
- 5778ffd MLBEDSW-2637 Refactor util funcs out of softmax.py by Michael McGeagh · 4 years, 1 month ago
- 22f74e1 MLBEDSW-2383 Preserve previous metadata by Michael McGeagh · 4 years, 1 month ago
- e99b893 MLBEDSW-2639: Moved the IFM/IFM2 order switch to register cmd stream generator by Jacob Bohlin · 4 years, 1 month ago
- ecd2052 MLBEDSW-2549 Crash with incorrect strided slice op by Michael McGeagh · 4 years, 1 month ago
- 36ffaf3 Skip the NOP resizebilinear op by Charles Xu · 4 years, 1 month ago
- bef228b [EXTAPI] exposing encode of biases to be consumed by an external API by Manupa Karunaratne · 4 years, 1 month ago
- a0c3624 [MLBEDSW-2335] SoftMax int16 by Fredrik Svedberg · 4 years, 3 months ago
- 9a03fdf MLBEDSW-2569:Support 1x1 IFM ResizeBilinear by Charles Xu · 4 years, 2 months ago
- 0430882 MLBEDSW-2574: Fix issue with different bias tensor scaling by Tim Hall · 4 years, 1 month ago
- 8677e53 vela: Fix numpy deprecation warning by Michael McGeagh · 4 years, 1 month ago
- b424974 vela: Protect against divide by zero by Michael McGeagh · 4 years, 1 month ago
- 775e396 test: Add extra print for verbose subgraphs by Michael McGeagh · 4 years, 1 month ago
- 2da7d11 vela: Ignore __pycache__ folders by Michael McGeagh · 4 years, 1 month ago
- 7b245fd MLBEDSW-2603 Missing "new_shape" attrib in Reshape by Michael McGeagh · 4 years, 1 month ago
- 8d939c0 MLBEDSW-2660 Convert FC-like convs to FC by Michael McGeagh · 4 years, 1 month ago
- 6a8d424 vela: Move common functionality by Michael McGeagh · 4 years, 1 month ago
- d83d2e1 [EXTAPI] refactor weight compression to be used by an external consumer by Manupa Karunaratne · 4 years, 1 month ago
- ebe26c7 MLBEDSW-1538: Output diff for elementwise min/max by Dwight Lidman · 4 years, 3 months ago
- 68a04b1 MLBEDSW-2641: Fix crash for network with only CPU ops by Jacob Bohlin · 4 years, 1 month ago
- 9b64ba0 MLBEDSW-2584: Support cascading of Transpose Convolution by Jacob Bohlin · 4 years, 2 months ago
- 9fbc491 MLBEDSW-1497: Add Quantize operator support by Jacob Bohlin · 4 years, 2 months ago
- 0b9ca78 Minor black code clean-up by Jacob Bohlin · 4 years, 2 months ago
- 5ff9944 MLBEDSW-2634 Avoid encoding empty weights stream by Patrik Gustavsson · 4 years, 2 months ago
- d89c09e MLBEDSW-2625 Alignment of tensor for bias and scale by Patrik Gustavsson · 4 years, 2 months ago
- ea49945 MLBEDSW-2615: MLCE: Ethos-U55 Flash usage increases due to Yoda Beta by Tim Hall · 4 years, 2 months ago
- 3ab9452 MLBEDSW-2551 Add support for more mem-cfgs by Patrik Gustavsson · 4 years, 2 months ago
- e843d33 MLBEDSW-2548: Fix for Double Buffer size estimate by Jacob Bohlin · 4 years, 2 months ago
- 42e4189 MLBEDSW-2600: Fix writing of register for wrong architecture by Tim Hall · 4 years, 2 months ago
- 04ce34c MLBEDSW-2340: Make the tensor address default None by Charles Xu · 4 years, 2 months ago
- 5f47c05 MLBEDSW-2564 Restrict settings of perm. storage by Patrik Gustavsson · 4 years, 2 months ago
- 8c32e15 MLBEDSW-2575: Update documentation for Yoda Beta by Tim Hall · 4 years, 2 months ago 1.1.0 1.1.0.rc2
- b02c8d9 MLBEDSW-2552: Skip npu cycle calculation for cpu op by Charles Xu · 4 years, 2 months ago 1.1.0.rc1
- 6231676 MLBEDSW-2556: Odd core/block depth weight interleaving update by Tim Hall · 4 years, 2 months ago
- f7e810a vela: MLBEDSW-828 weight/scale stream interleaving by Tim Hall · 4 years, 2 months ago
- eca2e95 MLBEDSW-2306 Added more supported mem-cfgs by Patrik Gustavsson · 4 years, 3 months ago
- eec4e50 MLBEDSW-2547 Add accelerator_configs by Patrik Gustavsson · 4 years, 2 months ago
- 83dec5c Update arch to 1.0.1 by Douglas Troha · 4 years, 2 months ago
- e76a533 doc: Add PyPi information to README.md by Tim Hall · 4 years, 2 months ago
- e4fd480 doc: Remove remains of a merge-conflict in OPTIONS.md by Jacob Bohlin · 4 years, 2 months ago 1.0.0
- 2a7ebe3 vela: Fix block config override issue. by Tim Hall · 4 years, 2 months ago
- c8310b1 MLBEDSW-2528: MLCE-219: Custom operator pass through by Tim Hall · 4 years, 2 months ago
- 10a6618 MLBEDSW-2062: Add EAC release notes by Tim Hall · 4 years, 2 months ago
- 70cc121 MLBEDSW-2506: Swap broadcast input if applicable by Charles Xu · 4 years, 2 months ago
- c30f495 Code clean-up using black and flake8 by Tim Hall · 4 years, 2 months ago
- 0fc46dc tools: Fix pytest-cov in pre-commit by Tim Hall · 4 years, 2 months ago
- 678645b MLBEDSW-2436: Support for HardSwish operator by Louis Verhaard · 4 years, 2 months ago
- 19515e8 MLBEDSW-2432: Retain pass order for CPU subgraph by Charles Xu · 4 years, 3 months ago
- c65cb6c Added --nhcwb16-between-cascaded-passes to OPTIONS.md by Jacob Bohlin · 4 years, 2 months ago
- 611fcdf MLBEDSW-2435: Fix for cascading upscaling operators by Jacob Bohlin · 4 years, 2 months ago
- 749d921 MLBEDSW-2468: Rounding 16bit scale multiplier by 0.5 by Charles Xu · 4 years, 2 months ago
- 7b8823f MLBEDSW-2370: Add CLI option for NHCWB16 by Charles Xu · 4 years, 3 months ago
- 332a704 MLBEDSW-2475: leaky relu not handling negative alpha value by Dwight Lidman · 4 years, 2 months ago
- ec74fd8 MLBEDSW-2061: Document CLI Options by Jacob Bohlin · 4 years, 3 months ago
- c88a96f MLBEDSW-2455: Bug fix int16 elementwise with scalar by Louis Verhaard · 4 years, 3 months ago
- e0ef273 MLBEDSW-2379: Fix 1-element tensors that were marked as scalars by Louis Verhaard · 4 years, 3 months ago
- 284223e MLBEDSW-2471: Remove unused CLI options by Tim Hall · 4 years, 3 months ago
- f1b67de MLBEDSW-2063: Add contributions guidelines by Tim Hall · 4 years, 3 months ago
- 93dc553 MLBEDSW-2388: Bug fix cascaded pooling by Louis Verhaard · 4 years, 3 months ago
- 465582c vela: Fix tensor purpose for some CPU only ops by Tim Hall · 4 years, 3 months ago
- 600351a MLBEDSW-1828: Ifm/ifm2 order is reversed in some cases of split by Charles Xu · 4 years, 3 months ago
- e1a5610 MLBEDSW-2232: Update Readme with security info by Tim Hall · 4 years, 3 months ago
- 25f605c vela: Add support for CPU only networks by Tim Hall · 4 years, 3 months ago
- cf7da10 MLBEDSW-1716: Transpose Convolution support by Jacob Bohlin · 4 years, 3 months ago
- 5b3dcd7 MLBEDSW-2269: Fix the buffer overlap issue for multi subgraphes by Charles Xu · 4 years, 3 months ago
- b2fb212 MLBEDSW-2420: Improved support for dilated convolution by Louis Verhaard · 4 years, 3 months ago
- 3c07c97 MLBEDSW-1941: Bug fix shared weights by Louis Verhaard · 4 years, 4 months ago
- 86d4993 MLBEDSW-2434: optim: 19_12_32, bilinear + depthwise int8 output diff by Dwight Lidman · 4 years, 3 months ago
- 42fed94 MLBEDSW-2372: Failing assert for ResizeBilinear with upscale != 2x by Dwight Lidman · 4 years, 3 months ago
- a9390f7 MLBEDSW-1971: Verify ifm block size calculation against specification by Dwight Lidman · 4 years, 3 months ago