Gitiles
Code Review Sign In
review.mlplatform.org / ml / ethos-u / ethos-u-vela / a71efe00bcbac0e601a0e3812bba89da452f2aff
  1. a71efe0 MLBEDSW-7754: Performance estimator is not using write/read shapes by William Isaksson · 10 months ago 3.9.0.rc1
  2. 81b765d MLBEDSW-7626: Add constraint for PAD op paddings by Johan Gunnarsson · 9 months ago
  3. cd03504 MLBEDSW-7689: Document verbose command stream options by Tim Hall · 9 months ago
  4. 4bd28aa MLBEDSW-7656: Update Python versions in README by Tim Hall · 10 months ago
  5. 631f600 MLBEDSW-7865: Vela duplicates outputs by William Isaksson · 10 months ago
  6. ea8c537 MLBEDSW-7681: Add Vela version to output file by William Isaksson · 11 months ago
  7. e4d5767 MLBEDSW-7846: Number of CPU Ops reported is wrong by William Isaksson · 10 months ago
  8. 2ff8c45 MLBEDSW-7397: Wrong mem_area used in scheduler by wilisa01 · 1 year ago
  9. a4f8411 MLBEDSW-7718: Add cmd1 payload legality checks by William Isaksson · 11 months ago
  10. 2f9b687 MLBEDSW-7165: Update to TensorFlow 2.12 by William Isaksson · 10 months ago
  11. 9cf63a3 MLBEDSW-7756: MLCE: Grouped convolutions runtime problem by Tim Hall · 11 months ago
  12. da8741a MLBEDSW-7653: Extend Mean support for depth axis by Alexander Hansson · 11 months ago
  13. 1d5e859 MLBEDSW-7652: Add mean support for batch and channel when shape is 1 by Alexander Hansson · 11 months ago
  14. ca9cc42 MLBEDSW-7728: Fix DMA_WAITs in register_command_stream_generator by Alexander Hansson · 11 months ago
  15. 8df91f5 MLBEDSW-7833: MLCE: Fixed output diff for reshape op by Johan Alfven · 10 months ago
  16. 52afbbb MLBEDSW-7752: setting query shapes to Shape4D(0) by William Isaksson · 11 months ago
  17. 762d3ac MLBEDSW-7832: test_tflite_model_semantic converting array to scalar by Tim Hall · 10 months ago
  18. 2d54e5c MLBEDSW-7716: Improve register level unit tests by Alexander Hansson · 11 months ago
  19. 6620714 MLBEDSW-7449: Add function description and type annotations by Raul Farkas · 12 months ago
  20. 90c34b5 MLBEDSW-7654: Extend support for Mean where HxW > 4096 by Alexander Hansson · 12 months ago
  21. 85b7790 MLBEDSW-7709: MLCE: Crash when rewriting split op by Johan Alfven · 11 months ago
  22. 3e7157b MLBEDSW-7315: Add support for AvgPool with stride_width > 3 by Raul Farkas · 1 year ago
  23. 3b64f06 MLBEDSW-7648: Fix bug with filter padding in conv2d by Raul Farkas · 12 months ago
  24. 5d24821 MLBEDSW-7531: Remove npu_block_type on unsupported ops by Raul Farkas · 12 months ago
  25. 8da4f95 MLBEDSW-7734: Update Sized import from collections by Rickard Bolin · 11 months ago
  26. 8e525ca MLBEDSW-7748: Add RSQRT support by Johan Alfven · 1 year ago
  27. c2c3063 MLBEDSW-7147: Enable weight buffering when opt for Size by Johan Alfven · 1 year, 2 months ago
  28. 0b4ac76 MLBEDS-7714: Fix assert for cascaded Resize op by Johan Alfven · 11 months ago
  29. 6c33985 MLBEDSW-7600: MLCE: Enable cascading for resize ops by Johan Alfven · 1 year ago
  30. 5200bd8 MLBEDSW-7528: Update documentation on verbose options by Rickard Bolin · 1 year ago 3.8.0 3.8.0.rc3
  31. fd27111 MLBEDSW-7494: Update release notes by Tim Hall · 12 months ago 3.8.0.rc2
  32. e8fc214 MLBEDSW-7230: Increase support for 1x1 ResizeBilinear with half_pixel_center=True by Alexander Hansson · 1 year ago
  33. 2466d81 MLBEDSW-7651: Include license in generated SUPPORTED_OPS.md by Alexander Hansson · 12 months ago
  34. 5ff4cd1 MLBEDSW-7223: Fusing Pad and AvgPool causes diff by Tim Hall · 12 months ago
  35. 0426fe9 MLBEDSW-7613: Crash when compiling model with resource variables by Johan Alfven · 12 months ago
  36. 3e7d544 MLBEDSW-7579: Fix test_build.py test issues by Raul Farkas · 1 year ago
  37. 1c54ac1 MLBEDSW-7390: Add verbose progress option by Raul Farkas · 1 year, 1 month ago
  38. fd6f624 MLBEDSW-7428: Remove unused rescale_for_faf by Rickard Bolin · 1 year ago
  39. 8e74b57 MLBEDSW-7546: Update lxml version to >= 4.5.2 by Alexander Hansson · 1 year ago 3.8.0.rc1
  40. d514a85 MLBEDSW-7490: Update documented python version to 3.9 by Alexander Hansson · 1 year ago
  41. 10d6b3b MLBEDSW-7283: Add opt cases for strided CONV2D by Raul Farkas · 1 year, 3 months ago
  42. 69782af Revert "MLBEDSW-6343: Remove op_index constraint" by Raul Farkas · 1 year ago
  43. ac11110 MLBEDSW-7578: Fix output diff caused by wrong rounding in Conv2d by Johan Alfven · 1 year ago
  44. 5fd155e MLBEDSW-7572 Update LSTM with new constant precision by Fredrik Svedberg · 1 year ago
  45. fe85315 MLBEDSW-7385: Unbound local var bug fix by Raul Farkas · 1 year, 2 months ago
  46. 7ede317 MLBEDSW-7542: Fix output diff caused by wrong scaling in Conv2d by Johan Alfven · 1 year ago
  47. 0a7d5ee MLBEDSW-7504: Vela does not keep op version number by wilisa01 · 1 year, 1 month ago
  48. 50550d6 MLBEDSW-7271: Add license headers to md files by Raul Farkas · 1 year, 2 months ago
  49. 5442544 MLBEDSW-7450: Fix NumPy out-of-bound conversion warning by Raul Farkas · 1 year, 1 month ago
  50. 4ac8b95 MLBEDSW-4178: Add automatic tag handling tests by Raul Farkas · 1 year, 2 months ago
  51. 439630f MLBEDSW-7416: per_layer_csv has extra row by wilisa01 · 1 year, 2 months ago
  52. 6fcc1f6 MLBEDSW-7234: Vela assert on int16 Min+Relu by wilisa01 · 1 year, 3 months ago
  53. da67f51 MLBEDSW-7545: Fix assert when serializing a tensor by Johan Alfven · 1 year ago
  54. ce50273 MLBEDSW-2082: Add Exp support by Johan Alfven · 1 year, 1 month ago
  55. 463f74b MLBEDSW-7443: Temporal mem usage is erroneously calculated by Johan Alfven · 1 year, 2 months ago
  56. 1070636 MLBEDSW-7503: Avoid changing buffer index for models with only CPU ops by Johan Alfven · 1 year, 1 month ago
  57. bb46af7 MLBEDSW-7530: Enable int16 input precision for mean operator by Rickard Bolin · 1 year, 1 month ago
  58. a68b82a MLBEDSW-7527: Mean operator output diff by Rickard Bolin · 1 year, 1 month ago
  59. 3fd5d83 MLBEDSW-6954: Update to TensorFlow 2.11 by Rickard Bolin · 1 year, 1 month ago
  60. c4268bf MLBEDSW-7501: Vela unnecessary adds reshaped weights tensors by Johan Alfven · 1 year, 1 month ago
  61. 301ca60 MLBEDSW-7458: Fused activation not passed through correctly by Johan Alfven · 1 year, 1 month ago
  62. 2f18e17 MLBEDSW-7373: Vela sometimes write empty buffers in incorrect format by Tim Hall · 1 year, 1 month ago
  63. 2180a17 MLBEDSW-7408: MLCE: Crash when serialising model LSTM by Tim Hall · 1 year, 2 months ago
  64. 7b3008a MLBEDSW-7487: Updated implementation for the Mean op by Johan Alfven · 1 year, 1 month ago
  65. 0ac0804 MLBEDSW-7196 Add LSTM support by Fredrik Svedberg · 1 year, 1 month ago
  66. c1ad80b MLBEDSW-7437: Add 64-bit output support for ArgMax by Johan Alfven · 1 year, 1 month ago
  67. 347c57b MLBEDSW-7442: Removed ofm quantization for ArgMax by Johan Alfven · 1 year, 1 month ago
  68. 56811e6 MLBEDSW-7439: Add support for input dims < 4 for ArgMax by Johan Alfven · 1 year, 2 months ago
  69. 72c6a24 MLBEDSW-6343: Remove op_index constraint by Raul Farkas · 1 year, 2 months ago
  70. 430002d MLBEDSW-7429: Add dev dependencies by Raul Farkas · 1 year, 2 months ago
  71. fcda685 MLBEDSW-4178: Add automatic tag handling by Raul Farkas · 1 year, 2 months ago
  72. 6986a07 MLBEDSW-6435: Implement support for ArgMax along depth dimension by Rickard Bolin · 1 year, 5 months ago
  73. 3340a88 MLBEDSW-7430: Remove non local mem usage from cascade info by Johan Alfven · 1 year, 2 months ago
  74. 126558e MLBEDSW-7352: Refactoring move_constant_data by Johan Alfven · 1 year, 2 months ago
  75. a5e1b62 MLBEDSW-7312: Refactoring bypass_memory_only_ops by Johan Alfven · 1 year, 3 months ago
  76. 9072496 MLBEDSW-6260: Add support for using DMA to copy feature maps by Johan Alfven · 1 year, 3 months ago
  77. bb98851 MLBEDSW-7427 Fix scale calculations for FullyConnected by Fredrik Svedberg · 1 year, 2 months ago
  78. 6e281af MLBEDSW-7393: MLCE: Optimize compile time for large networks by Johan Alfven · 1 year, 3 months ago
  79. c72cac8 MLBEDSW-7386: Fix assert in pass packing by Johan Alfven · 1 year, 2 months ago
  80. 3ac03be MLBEDSW-7396: MLCE: Add num elements constraint on reshape by Johan Alfven · 1 year, 2 months ago
  81. c60b7e3 MLBEDSW-7094: Update release notes by Tim Hall · 1 year, 3 months ago 3.7.0 3.7.0.rc2
  82. bfe6fe3 MLBEDSW-7347: MLCE: Split followed by elementwise op will assert by Johan Alfven · 1 year, 3 months ago
  83. d0e41cf MLBEDSW-7343: MLCE: Unsupported STRIDED_SLICE with negative index and shrinking an axis by Tim Hall · 1 year, 3 months ago
  84. 46c9477 MLBEDSW-7211: Convert fixup_asymmetric_weights to supported ops check by wilisa01 · 1 year, 3 months ago
  85. 16b5e5e MLBEDSW-7342: Regression: Output diff for mlperf_deeplabv3_mnv2_ade20k_int8 by wilisa01 · 1 year, 3 months ago
  86. 9070f0f MLBEDSW-7316: Fix crash for networks with resource variables by Johan Alfven · 1 year, 3 months ago
  87. 33c01e6 MLBEDSW-7274 Add support for Variable Tensors by Fredrik Svedberg · 1 year, 3 months ago
  88. 4939633 MLBEDSW-7250: pytest RuntimeWarning: overflow encountered in float_scalars by wilisa01 · 1 year, 3 months ago
  89. 899500d MLBEDSW-7100: Update mlw_codec copyright years by Rickard Bolin · 1 year, 3 months ago
  90. 8289d51 MLBEDSW-4960: convert_resizebilinear_1x1_to_add creates constant output tensor by wilisa01 · 1 year, 4 months ago
  91. 428a8d5 MLBEDSW-6982: Move to setup.cfg and pyproject.toml by Raul Farkas · 1 year, 4 months ago 3.7.0.rc1
  92. 59b9ab9 MLBEDSW-7331: Reinstate max stride height constraint of 3 for Conv2D by Raul Farkas · 1 year, 3 months ago
  93. 1c59048 MLBEDSW-7281: create_const_tensor OverflowError on Microsoft Windows by Tim Hall · 1 year, 4 months ago
  94. 090f18a MLBEDSW-7237: CONV_2D stride 4 optimisation by Raul Farkas · 1 year, 4 months ago
  95. 12e4811 MLBEDSW-7284: MLCE: Fix assert for faulty Split op by Johan Alfven · 1 year, 3 months ago
  96. 4b71799 Revert "MLBEDSW-6954: Update to TensorFlow 2.11" by Rickard Bolin · 1 year, 3 months ago
  97. 82593de MLBEDSW-6954: Update to TensorFlow 2.11 by wilisa01 · 1 year, 5 months ago
  98. 3b1578e MLBEDSW-7151: MLCE: Difference in model output between x86 & aarch64 by Tim Hall · 1 year, 4 months ago
  99. f349047 MLBEDSW-7091: MLCE: Reduce SRAM, compiling for Performance by Johan Alfven · 1 year, 4 months ago
  100. 78fc9bc MLBEDSW-7231: MLCE: Fixed assert caused by multiple reshape op's by Johan Alfvén · 1 year, 4 months ago