1. f697eac MLBEDSW-8725: Remove scales & biases from --verbose-weights by Alexander Bengtsson · 5 weeks ago main
  2. b90666d TOSA fixes by Oscar Andersson · 4 weeks ago
  3. 9341bf4 MLBEDSW-8749: MLCE: Output diff on strided slice by Johan Alfven · 3 weeks ago
  4. f19fd2f Fix stats writer exception when op has no tensors by Simon Hollis · 4 weeks ago
  5. 78b9412 Modifications of rescale to enable basic form quantized network support. by Rob Elliott · 9 weeks ago
  6. cc82c36 MLBEDSW-8704: Update release notes by Rickard Bolin · 5 weeks ago 3.11.0 3.11.0.rc2
  7. 3368308 MLBEDSW-8674: int16 VectorProduct should use Natural rounding by Johan Alfven · 7 weeks ago 3.11.0.rc1
  8. 646314e MLBEDSW-8620: Fix MirrorPad supported ops check by Rickard Bolin · 8 weeks ago
  9. fdbb072 MLBEDSW-8491: Add support for Mirror pad by Rickard Bolin · 7 months ago
  10. 014bc28 MLBEDSW-8569: MLCE: Reported number of CPU ops are wrong by Johan Alfven · 9 weeks ago
  11. cbec599 MLBEDSW-8575 Tests fails on conv networks by Fredrik Svedberg · 9 weeks ago
  12. 1c8f92d vela: Remove unnecessary code from architecture allocator by Tim Hall · 9 weeks ago
  13. b982898 Revert "MLBEDSW-8468: overlaps_ranges does not treat the live range end time as inclusive" by Tim Hall · 10 weeks ago
  14. e4d0dbf vela: Remove dead code from register command stream by Tim Hall · 2 months ago
  15. c222f8c MLBEDSW-8568 Fix mlw_codec memory handling by Fredrik Svedberg · 3 months ago
  16. 56e5f0c CONV ops int16 tests failed after TensorFlow update by William Isaksson · 3 months ago
  17. 84fe2f6 MLBEDSW-8468: overlaps_ranges does not treat the live range end time as inclusive by Tim Hall · 3 months ago
  18. 37dbca2 MLBEDSW-8497: [MLCE] Avoid modifying FC with dynamic weights by Johan Alfven · 3 months ago
  19. f4a511f MLBEDSW-8157: Update to TensorFlow 2.15 by William Isaksson · 4 months ago
  20. d2e03c6 MLBEDSW-8467: verbose-allocation memory usage is incorrect by Tim Hall · 3 months ago
  21. 6165283 MLBEDSW-7871: Document new error types in API by William Isaksson · 8 months ago
  22. 8cb3c36 MLBEDSW-8109: Update release notes by Tim Hall · 4 months ago 3.10.0 3.10.0.rc2
  23. 5aa9ae2 MLBEDSW-8240: Document reference comparison point by Tim Hall · 4 months ago
  24. 2742947 MLBEDSW-8280: Update PyPI homepage link by Tim Hall · 4 months ago
  25. 6a7fd3d Vela: Update from using deprecated pkg_resources by Tim Hall · 6 months ago
  26. 32cdbbb MLBEDSW-8336: MLCE: Update example for CPU Tensor Alignment by Johan Alfven · 4 months ago
  27. f49b6e2 MLBEDSW-8326: MLCE: Update constraint message for AVERAGE_POOL_2D by Johan Alfven · 4 months ago
  28. f418e83 MLBEDSW-8317: Add semantic checks for Transpose by Johan Alfven · 5 months ago
  29. a8fda88 MLBEDSW-8290: MLCE: Add TRANSPOSE support by Johan Alfven · 5 months ago 3.10.0.rc1
  30. 4bf0cdf MLBEDSW-8261: Fix regression on AvgPool by Johan Alfven · 5 months ago
  31. 199e8e6 MLBEDSW-8117: Incorrect stride check for IFM/IFM2 and OFM by Björn Davidsson · 6 months ago
  32. 67daf2a MLBEDSW-8219: Activation can not be fused with dma operation by Johan Alfven · 5 months ago
  33. afb56ae MLBEDSW-8201: [MLCE] Extended stride support for CONV_2D by Johan Alfven · 5 months ago
  34. 909923a MLBEDSW-8156: Update max_outstanding_kernels to 2 by Rickard Bolin · 5 months ago
  35. b37a81b MLBEDSW-8111: Update to TensorFlow 2.14 by Rickard Bolin · 6 months ago
  36. 529b787 MLBEDSW-7853: Missing options for RANDOM_UNIFORM operator by Rickard Bolin · 8 months ago
  37. f4aa7f7 MLBEDSW-8064: Update Markdown URLs by Johan Gunnarsson · 6 months ago
  38. 7972ee8 MLBEDSW-8102: Fix regression on Argmax int64 by Johan Alfven · 6 months ago
  39. a5da0ab MLBEDSW-8052: Update FlatBuffers version pin in pyproject.toml by William Isaksson · 6 months ago
  40. 906c9e8 MLBEDSW-8042: MLCE: Add SQUARED_DIFFERENCE support by Johan Alfven · 10 months ago
  41. b4e804b MLBEDSW-8010: Refine fixup_pool_strides to also check stride by Johan Gunnarsson · 7 months ago
  42. 7ccc583 MLBEDSW-8003: Limit fixup_pool_strides to AvgPool and MaxPool by Johan Gunnarsson · 7 months ago
  43. f0cb1ab MLBEDSW-8035: Update to TensorFlow 2.13 by William Isaksson · 7 months ago
  44. c0bb868 MLBEDSW-7997: [MLCE] Extended stride support for TRANSPOSE CONV by Johan Alfven · 7 months ago
  45. 26c8e84 MLBEDSW-7541: Extend error message when reaching maximum recursion depth by Rickard Bolin · 11 months ago
  46. 24570f0 MLBEDSW-7968: Add fixup for strides when kernel size equals IFM shape by Johan Gunnarsson · 7 months ago
  47. 9855637 MLBEDSW-7881: Convert Quantize op to Avgpool op in graph optimiser by Johan Gunnarsson · 8 months ago
  48. c02eaa3 MLBEDSW-7949: [MLCE] Remove duplicate cpu tensors by Johan Alfven · 7 months ago
  49. 00a15db Moving Vela to use TOSA v0.80.0 specification by Rob Elliott · 7 months ago
  50. 8ea90ed MLBEDSW-7702: Update release notes by Rickard Bolin · 8 months ago 3.9.0
  51. 3db30ff MLBEDSW-7884: Fix crash for RSQRT by Johan Alfven · 8 months ago 3.9.0.rc2
  52. 75d3402 MLBEDSW-7832: test_tflite_model_semantic converting array to scalar by William Isaksson · 8 months ago
  53. a71efe0 MLBEDSW-7754: Performance estimator is not using write/read shapes by William Isaksson · 9 months ago 3.9.0.rc1
  54. 81b765d MLBEDSW-7626: Add constraint for PAD op paddings by Johan Gunnarsson · 8 months ago
  55. cd03504 MLBEDSW-7689: Document verbose command stream options by Tim Hall · 8 months ago
  56. 4bd28aa MLBEDSW-7656: Update Python versions in README by Tim Hall · 8 months ago
  57. 631f600 MLBEDSW-7865: Vela duplicates outputs by William Isaksson · 8 months ago
  58. ea8c537 MLBEDSW-7681: Add Vela version to output file by William Isaksson · 9 months ago
  59. e4d5767 MLBEDSW-7846: Number of CPU Ops reported is wrong by William Isaksson · 8 months ago
  60. 2ff8c45 MLBEDSW-7397: Wrong mem_area used in scheduler by wilisa01 · 11 months ago
  61. a4f8411 MLBEDSW-7718: Add cmd1 payload legality checks by William Isaksson · 9 months ago
  62. 2f9b687 MLBEDSW-7165: Update to TensorFlow 2.12 by William Isaksson · 8 months ago
  63. 9cf63a3 MLBEDSW-7756: MLCE: Grouped convolutions runtime problem by Tim Hall · 9 months ago
  64. da8741a MLBEDSW-7653: Extend Mean support for depth axis by Alexander Hansson · 9 months ago
  65. 1d5e859 MLBEDSW-7652: Add mean support for batch and channel when shape is 1 by Alexander Hansson · 9 months ago
  66. ca9cc42 MLBEDSW-7728: Fix DMA_WAITs in register_command_stream_generator by Alexander Hansson · 9 months ago
  67. 8df91f5 MLBEDSW-7833: MLCE: Fixed output diff for reshape op by Johan Alfven · 9 months ago
  68. 52afbbb MLBEDSW-7752: setting query shapes to Shape4D(0) by William Isaksson · 10 months ago
  69. 762d3ac MLBEDSW-7832: test_tflite_model_semantic converting array to scalar by Tim Hall · 9 months ago
  70. 2d54e5c MLBEDSW-7716: Improve register level unit tests by Alexander Hansson · 9 months ago
  71. 6620714 MLBEDSW-7449: Add function description and type annotations by Raul Farkas · 10 months ago
  72. 90c34b5 MLBEDSW-7654: Extend support for Mean where HxW > 4096 by Alexander Hansson · 10 months ago
  73. 85b7790 MLBEDSW-7709: MLCE: Crash when rewriting split op by Johan Alfven · 10 months ago
  74. 3e7157b MLBEDSW-7315: Add support for AvgPool with stride_width > 3 by Raul Farkas · 11 months ago
  75. 3b64f06 MLBEDSW-7648: Fix bug with filter padding in conv2d by Raul Farkas · 11 months ago
  76. 5d24821 MLBEDSW-7531: Remove npu_block_type on unsupported ops by Raul Farkas · 10 months ago
  77. 8da4f95 MLBEDSW-7734: Update Sized import from collections by Rickard Bolin · 10 months ago
  78. 8e525ca MLBEDSW-7748: Add RSQRT support by Johan Alfven · 11 months ago
  79. c2c3063 MLBEDSW-7147: Enable weight buffering when opt for Size by Johan Alfven · 1 year ago
  80. 0b4ac76 MLBEDS-7714: Fix assert for cascaded Resize op by Johan Alfven · 10 months ago
  81. 6c33985 MLBEDSW-7600: MLCE: Enable cascading for resize ops by Johan Alfven · 11 months ago
  82. 5200bd8 MLBEDSW-7528: Update documentation on verbose options by Rickard Bolin · 11 months ago 3.8.0 3.8.0.rc3
  83. fd27111 MLBEDSW-7494: Update release notes by Tim Hall · 11 months ago 3.8.0.rc2
  84. e8fc214 MLBEDSW-7230: Increase support for 1x1 ResizeBilinear with half_pixel_center=True by Alexander Hansson · 11 months ago
  85. 2466d81 MLBEDSW-7651: Include license in generated SUPPORTED_OPS.md by Alexander Hansson · 11 months ago
  86. 5ff4cd1 MLBEDSW-7223: Fusing Pad and AvgPool causes diff by Tim Hall · 11 months ago
  87. 0426fe9 MLBEDSW-7613: Crash when compiling model with resource variables by Johan Alfven · 11 months ago
  88. 3e7d544 MLBEDSW-7579: Fix test_build.py test issues by Raul Farkas · 11 months ago
  89. 1c54ac1 MLBEDSW-7390: Add verbose progress option by Raul Farkas · 11 months ago
  90. fd6f624 MLBEDSW-7428: Remove unused rescale_for_faf by Rickard Bolin · 11 months ago
  91. 8e74b57 MLBEDSW-7546: Update lxml version to >= 4.5.2 by Alexander Hansson · 11 months ago 3.8.0.rc1
  92. d514a85 MLBEDSW-7490: Update documented python version to 3.9 by Alexander Hansson · 11 months ago
  93. 10d6b3b MLBEDSW-7283: Add opt cases for strided CONV2D by Raul Farkas · 1 year, 2 months ago
  94. 69782af Revert "MLBEDSW-6343: Remove op_index constraint" by Raul Farkas · 11 months ago
  95. ac11110 MLBEDSW-7578: Fix output diff caused by wrong rounding in Conv2d by Johan Alfven · 11 months ago
  96. 5fd155e MLBEDSW-7572 Update LSTM with new constant precision by Fredrik Svedberg · 11 months ago
  97. fe85315 MLBEDSW-7385: Unbound local var bug fix by Raul Farkas · 1 year ago
  98. 7ede317 MLBEDSW-7542: Fix output diff caused by wrong scaling in Conv2d by Johan Alfven · 11 months ago
  99. 0a7d5ee MLBEDSW-7504: Vela does not keep op version number by wilisa01 · 12 months ago
  100. 50550d6 MLBEDSW-7271: Add license headers to md files by Raul Farkas · 1 year ago