Gitiles
Code Review Sign In
review.mlplatform.org / tosa / reference_model / b5fcfc0cfeffeb3fe9f05c32dc678ab09b2cee31 / reference_model / src / ops
  1. b5fcfc0 [reference_model] Remove output_shape from transpose_conv2d by Suraj Sudhir · 9 weeks ago
  2. 1eb1455 Update compliance verify checks by Jeremy Johnson · 10 weeks ago
  3. 0306fb6 RFFT2D, refmodel. Correct code when size is one by Dmitriy Smirnov · 10 weeks ago
  4. 5d0e9c7 [ref model] fix const/pad/clamp attribute serialization by Tai Ly · 2 months ago
  5. 0dac6c9 Fix the wrong QMax and QMin type assignment in rescale op by TatWai Chong · 3 months ago
  6. 9c0a507 Modify Rescale signedness check to look at attributes by Eric Kunze · 3 months ago
  7. 12159fc Show actual runtime value of shapeType tensors by Jerry Ge · 3 months ago
  8. 08fe7a5 Take into account of `output_unsigned` in rescale operation by TatWai Chong · 3 months ago
  9. f36f256 [ref model] Add acc_type to Conv Ops by Tai Ly · 3 months ago
  10. 60dc48c [ref model] Change Clamp and Pad attribute fields by Tai Ly · 3 months ago
  11. e67115e Add missing FP8 definition and instantiation for FULLY_CONNNECTED op by Won Jeon · 3 months ago
  12. 1adff83 Add INT48 and INT4 datatype support to IDENTITY by evacha01 · 3 months ago
  13. 6e1e2bc [ref model] Change RescaleOp attrs to inputs by Tai Ly · 4 months ago
  14. 51bd4f5 Add Tosa Sin/Cos operators by Jerry Ge · 4 months ago
  15. 0a04299 Testing support for MUL with shift as input by Jeremy Johnson · 4 months ago
  16. 3195a66 Fix padding value for PAD op and tensor writing to npy for FP8 by Won Jeon · 4 months ago
  17. 8ead6c4 [reference_model] tosa.fb name changes by Tai Ly · 4 months ago
  18. c5c2a7e [ref_model] Change resize attrs to inputs by Tai Ly · 4 months ago
  19. 97f1c0e Fix comparing unsigned int and int in slice evaluation by TatWai Chong · 4 months ago
  20. c7bfa58 Change the shift of mul to tensor type by TatWai Chong · 4 months ago
  21. 2c34b46 Add support for FP8 to reference model by Won Jeon · 4 months ago
  22. 59d8f50 Fix REDUCE ops to support 8k MAX_RANK by Jeremy Johnson · 4 months ago
  23. 6f57e6e Main Compliance: RFFT2D support by Jeremy Johnson · 5 months ago
  24. cbbbafa Main Compliance: Update POW error bound by Jeremy Johnson · 4 months ago
  25. c833081 Main Compliance: FFT2D support by Jeremy Johnson · 5 months ago
  26. 01f937a Change the start and size of slice to tosa shape type by TatWai Chong · 5 months ago
  27. e095da7 [ref model] Change PadOp's padding to Shape by Tai Ly · 5 months ago
  28. 66704d5 Fix logical right shift operator for signed negative integers by Won Jeon · 12 months ago
  29. 8690a08 [reference model] Add shape operators by Tai Ly · 6 months ago
  30. 48ed6cf CLAMP limits should be expressed in in_out_t by Eric Kunze · 5 months ago
  31. d80ea5e Main Conformance: Re-adjust TANH compliance check by Jeremy Johnson · 6 months ago
  32. d6a0461 Fix Cast Float to Int overflows by Jerry Ge · 6 months ago
  33. 44827be Fix Cast FP32 to Int32 Overflow by Jerry Ge · 6 months ago
  34. e1e611d Remove inferred dimension from RESHAPE by Jeremy Johnson · 6 months ago
  35. 598d74a Main Conformance: Adjust TANH compliance value by Jeremy Johnson · 6 months ago
  36. 194fe31 Enforce no output rewrite REQUIRE in SCATTER by Jeremy Johnson · 6 months ago
  37. 438ad7f Fix Format Specifiers for MUL REQUIRES output by Jack Frankland · 7 months ago
  38. 534923d Change TANH, SIGMOID to ABS_ERROR compliance by Jeremy Johnson · 7 months ago
  39. ac40bd1 Correct Fully Connected Validation Logic by Jack Frankland · 7 months ago
  40. 5637a86 Support loading shared libraries for custom operators by Jerry Ge · 8 months ago
  41. 9a75838 Main Compliance testing support for EXP & POW by Jeremy Johnson · 7 months ago
  42. fd8fde8 [reference_model] Add local_bound support by Tai Ly · 7 months ago
  43. 452ba70 Catch when CONSTs aren't initialized by Jeremy Johnson · 8 months ago
  44. 29e46cf Fix AvgPool2D regression by James Ward · 8 months ago
  45. 5a9e0cd Fix AVG_POOL2D bad_alloc with large kernel sizes by James Ward · 8 months ago
  46. fb87982 Add integer divide with floor for coordinate calculation by TatWai Chong · 10 months ago
  47. a8098c0 Support new RESCALE attributes by Eric Kunze · 10 months ago
  48. a21b2e8 Add DIM operator to reference model by Won Jeon · 10 months ago
  49. a641dd5 Add support for bias broadcasting by Tai Ly · 10 months ago
  50. be2e87c Update formatting based on clang-format 14 by Eric Kunze · 11 months ago
  51. 17fab3b Fix compiler warnings (NFC) by Eric Kunze · 11 months ago
  52. e5cabbf Enable lazy tensor allocation by Jerry Ge · 11 months ago
  53. 9c9c8da Run clang-format and update copyright by Jerry Ge · 11 months ago
  54. edac6ab Fix missing template instantiations by Eric Kunze · 12 months ago
  55. 78155c6 Add support for ERF operator to reference model by Won Jeon · 1 year ago
  56. 135c955 Add ERROR_IF to incorrect broadcast shapes by Jerry Ge · 1 year, 1 month ago
  57. eb52cc1 Add support for boolean outputs in model runner by Jiacheng Liang · 1 year, 1 month ago
  58. 307392a Add abs calculations under precise_mode by Tai Ly · 1 year, 1 month ago
  59. 264f7fa Add support for one dimension of size -1 in ReshapeOp by Jerry Ge · 1 year, 2 months ago
  60. 0bd4ec8 Refactor ref_model rank checking and add level check to argmax by Jerry Ge · 1 year, 2 months ago
  61. a4d748b [reference model] Add precise mode by Tai Ly · 1 year, 3 months ago
  62. 44eb88d AVG_POOL2D - Fix for stride renaming mistake by Jeremy Johnson · 1 year, 2 months ago
  63. a793f46 Add level checking to TOSA Ref model by Jerry Ge · 1 year, 2 months ago
  64. 4e9a977 [reference model] support multiple regions by Tai Ly · 1 year, 3 months ago
  65. cf305db Refactor 1L to INT64_C() by Jerry Ge · 1 year, 3 months ago
  66. 57bc079 Update CAST fp to int rounding by Eric Kunze · 1 year, 5 months ago
  67. a4e48ca Update rank limits for SLICE, TILE and TRANSPOSE by Luke Hutton · 1 year, 4 months ago
  68. 5728713 Add FFT2d to the reference model by Luke Hutton · 1 year, 4 months ago
  69. d34b3fc Remove accumulator attributes from all but AVG_POOL2D by James Ward · 1 year, 5 months ago
  70. 736fd1a Create MI tests for Type Conversion: CAST by James Ward · 1 year, 5 months ago
  71. 261b7b6 Add RFFT2d to the reference model by Luke Hutton · 1 year, 5 months ago
  72. eef8667 Fix for sign extending LOGICAL LEFT/RIGHT SHIFT results by Jeremy Johnson · 1 year, 5 months ago
  73. 3407125 Create MI tests for Activation: CLAMP; Data Layout: PAD by James Ward · 1 year, 6 months ago
  74. df628d4 Update for RESCALE spec apply_add clarification by Jeremy Johnson · 1 year, 5 months ago
  75. 9e94af8 Reference model update for control flow operators support by Jerry Ge · 1 year, 8 months ago
  76. 98c281f Add explicit template instantiations for abstract classes by Jared Smolens · 1 year, 6 months ago
  77. a682749 Fix reference model memory leaks for the following ops by Jerry Ge · 1 year, 7 months ago
  78. ee25669 FP16 improvements by James Ward · 1 year, 7 months ago
  79. a633bc6 Fix the floating point precision issue for Sigmoid FP32 by Jerry Ge · 1 year, 7 months ago
  80. 52460a8 Zero point addition in RESCALE should be int32 by Eric Kunze · 1 year, 7 months ago
  81. 24dbc42 Add BF16 support to reference model by James Ward · 1 year, 8 months ago
  82. bc2a3db Rename FLOAT type to FP32 by Jeremy Johnson · 1 year, 9 months ago
  83. 8b39043 Reference model changes for fp16 support by James Ward · 1 year, 10 months ago
  84. fd62905 Update framework test generator to support TF/TFL conv3d. by TatWai Chong · 1 year, 11 months ago
  85. c1a9783 Align padding for transpose_conv2d to match spec by Eric Kunze · 2 years ago
  86. d511f9e Enabled 16-bit TABLE REQUIRE statement by Jerry Ge · 1 year, 10 months ago
  87. 3c59d5d Check that the shape calculation for PAD is correct by Eric Kunze · 1 year, 10 months ago
  88. f732609 Update TOSA resize to match specification by TatWai Chong · 2 years ago
  89. f733783 Fix reference model use of weight zero point by Eric Kunze · 2 years ago v0.30 v0.30.0
  90. b5fabec Remove quantization info from serialization attributes by Eric Kunze · 2 years ago
  91. 24594f5 Update transpose_conv2d to align with TOSA spec by TatWai Chong · 2 years ago
  92. 61f6622 Remove dilation from transpose_conv2d op by Eric Kunze · 2 years, 1 month ago
  93. ec0327d Change size check in TILE to ERROR_IF by Eric Kunze · 2 years, 1 month ago
  94. 86c403b Align the serialization schema with TOSA 0.24.0 specification by TatWai Chong · 2 years ago
  95. c23fc3b Remove RESHAPE -1 dimensions support by Jeremy Johnson · 2 years, 1 month ago
  96. f7f78ae Add support for uint16_t to RESCALE by Jeremy Johnson · 2 years, 1 month ago
  97. 7edb34c Initialize accumulator with bias value for CONV3D by Eric Kunze · 2 years, 1 month ago
  98. 67a9155 Adjust divisor calculation by Eric Kunze · 2 years, 5 months ago
  99. 0e46364 Fix for NEGATE using 32-bit accumulator by Jeremy Johnson · 2 years, 2 months ago
  100. 4a6fb9b Update tensor ops ERROR_IF criteria by Jeremy Johnson · 2 years, 2 months ago