Gitiles
Code Review Sign In
review.mlplatform.org / tosa / specification / HEAD
  1. a578390 Fix logic error for RESCALE of uint16 by Eric Kunze · 1 year, 1 month ago
  2. 53e7659 Fix resize_t enum name by Kevin Petit · 1 year, 1 month ago
  3. bc72ba8 Move the tensor size limit into the level range definition by Dominic Symes · 1 year, 1 month ago
  4. 211c5f5 Generate level maximums from the XML by Kevin Petit · 1 year, 1 month ago
  5. e0fee3d Fix description of tensor size limit by Kevin Petit · 1 year, 1 month ago
  6. 544227e Add enumerations to TOSA specification by Eric Kunze · 1 year, 3 months ago
  7. 9bb5f5d Add missing MAX_RANK to NEGATE by Jeremy Johnson · 1 year, 1 month ago
  8. f28bd0a Update Argmax's rank maximum to MAX_RANK by Jerry Ge · 1 year, 2 months ago
  9. 6577bcd Fix typo in TILE attributes by Eric Kunze · 1 year, 2 months ago
  10. 67a6f7f Check the output shape of broadcast operations by Dominic Symes · 1 year, 2 months ago
  11. 1854892 SCATTER/GATHER: Replace value_t with in_out_t by Kevin Petit · 1 year, 2 months ago
  12. 6305460 Update version to 0.70.0 draft by Eric Kunze · 1 year, 2 months ago
  13. 68a3f7b Update version to 0.60.0 for release by Eric Kunze · 1 year, 2 months ago v0.60 v0.60.0
  14. 2fc810e Add int48 to the supported types for CONST by Eric Kunze · 1 year, 4 months ago
  15. 8f7688d Main inference conformance additions by Dominic Symes · 1 year, 3 months ago
  16. 580fdd1 Fix rank limits for various data layout operations by Luke Hutton · 1 year, 3 months ago
  17. 87bf309 Add accumulator size attribute to AVG_POOL2D by Eric Kunze · 1 year, 5 months ago
  18. c386a05 Main inference conformance draft by Dominic Symes · 1 year, 4 months ago
  19. 5bb1f02 Clarify description for LOGICAL_LEFT_SHIFT by Eric Kunze · 1 year, 4 months ago
  20. 13ede1d RFFT2D: Adjust output height to be same as the input by Luke Hutton · 1 year, 4 months ago
  21. a269fd4 SCATTER/GATHER: Remove redundant definition of index_t by Kevin Petit · 1 year, 5 months ago
  22. b7293ae SELECT: Replace use of cmp_t with bool_t by Kevin Petit · 1 year, 6 months ago
  23. 36f2d64 Use XML as source for specification version by Kevin Petit · 1 year, 5 months ago
  24. d19f7ff Update the version to 0.50.0 and remove the draft tag by Eric Kunze · 1 year, 6 months ago v0.50 v0.50.0
  25. 4370b93 Clarify the type of condition tensors by Dominic Symes · 1 year, 6 months ago
  26. e4d6a1b Add Levels defintion by Dominic Symes · 1 year, 7 months ago
  27. 1cf84e9 SLICE: remove the mention of an axis in the description by Kevin Petit · 1 year, 6 months ago
  28. 8cba323 RESCALE: Clarify zero-point addition by Dominic Symes · 1 year, 6 months ago
  29. 0205d99 Define the index type for tensor co-ordinates by Dominic Symes · 1 year, 7 months ago
  30. 2ceeaa2 Change RESIZE border attribute to int16_t by Eric Kunze · 1 year, 7 months ago
  31. 3c5f0e1 Add CAST between floating point types by Eric Kunze · 1 year, 8 months ago
  32. ccde4d7 RESIZE: Clarify floating point types by Dominic Symes · 1 year, 8 months ago
  33. 5bb9a2a Increment revision to 0.41 draft by Eric Kunze · 1 year, 8 months ago
  34. d5fcd0d Change version to 0.40.0 for next release by Eric Kunze · 1 year, 9 months ago v0.40 v0.40.0
  35. 8783adb RESCALE and POW: remove rank restriction by Dominic Symes · 1 year, 10 months ago
  36. eda7b12 TRANSPOSED_CONV2D: Invert pad definition by Dominic Symes · 1 year, 11 months ago
  37. 74a37ca Fix cut and paste error for MATMUL by Eric Kunze · 1 year, 9 months ago
  38. 52dd6bb Change convolution weights to always dynamic by Eric Kunze · 1 year, 9 months ago
  39. 58098a7 Machine parsable specification by Eric Kunze · 1 year, 10 months ago
  40. 6361d16 PAD: Check output shape by Dominic Symes · 1 year, 9 months ago
  41. 4b86786 RESIZE: define scale as a ratio of integers by Eric Kunze · 1 year, 11 months ago
  42. b8522ba Relax limit on input value for RESCALE by Eric Kunze · 1 year, 11 months ago
  43. 1718f3a Update revision to 0.31.0 draft by Eric Kunze · 1 year, 11 months ago
  44. f5ddd92 Update TOSA version to 0.30.0 by Eric Kunze · 1 year, 11 months ago v0.30 v0.30.0
  45. 4c6b3d8 Revert RESIZE behvior to the 0.23 version by Eric Kunze · 1 year, 11 months ago
  46. 42229d0 Initial work on floating-point type definition by Eric Kunze · 2 years, 1 month ago
  47. f9e5ba9 Rework the introduction by Eric Kunze · 2 years ago
  48. a177e43 Fix typo on CONV3D pseudocode by Eric Kunze · 2 years ago
  49. 0738025 Make the use of inverse in FFT2D definition consistent by Eric Kunze · 2 years ago
  50. 44a1347 Add FFT operators to MI/MT profiles by Eric Kunze · 2 years, 9 months ago
  51. 7e4148c RESIZE: Clarify offset and border ranges by Dominic Symes · 2 years ago
  52. 844b3b4 Update RESHAPE pseudocode by Eric Kunze · 2 years ago
  53. d8f725c Fix typo in TILE operator by Eric Kunze · 2 years ago
  54. eef012e Add the uint16_t data type by Eric Kunze · 2 years ago
  55. 6de9782 Mark RESCALE multiplier and scale as refs by Eric Kunze · 2 years ago
  56. 8a536ae Specify width of integer types for all operator arguments by Kevin Petit · 2 years, 1 month ago
  57. 8d8b035 RESIZE: Define scale as a ratio of integers by Dominic Symes · 2 years, 1 month ago
  58. 1aa244c Change from assignment to a check for output dims for tensor ops by Jeremy Johnson · 2 years, 1 month ago
  59. cb6c6b3 Specify width of integer types by Dominic Symes · 2 years, 1 month ago
  60. 5de08d1 Fix round argument category for ARITHMETIC_RIGHT_SHIFT by Kevin Petit · 2 years, 1 month ago
  61. 29fc289 Simple fixes to the arguments to CAST and RESCALE by Kevin Petit · 2 years, 1 month ago
  62. a6ac716 Specify output dimension formulae for tensor ops by Dominic Symes · 2 years, 1 month ago
  63. a1ba656 Update makefile to fail build on spelling failure by Eric Kunze · 2 years, 2 months ago
  64. 32c91b0 Update TRANSPOSE argument description by Eric Kunze · 2 years, 4 months ago
  65. ce6e02c Update floating point edge cases by Eric Kunze · 2 years, 2 months ago
  66. 2ff79fe TABLE: Clarify the interpolation slope range by Dominic Symes · 2 years, 4 months ago
  67. 3cb7535 apply_scale_32: adjust range checking by Dominic Symes · 2 years, 4 months ago
  68. c1e39d5 Simplify shape checking for TRANSPOSE by Eric Kunze · 2 years, 4 months ago
  69. e942f07 Fix range of C iteration in DEPTHWISE_CONV2D by Eric Kunze · 2 years, 4 months ago
  70. 2a3d560 Ensure ranks match in apply_broadcast by Eric Kunze · 2 years, 5 months ago
  71. a3eded0 Add rudimentary spell check for specification by Eric Kunze · 2 years, 5 months ago
  72. f734f1b Fix typo in TOSA license by Eric Kunze · 2 years, 5 months ago
  73. 3747fda RESIZE: Clarify output dimensions by Dominic Symes · 2 years, 7 months ago
  74. d4cf073 MUL: Correct code for the case of value2<0 by Dominic Symes · 2 years, 6 months ago
  75. a0e9a52 Use in_out_t when a type is used for input and output by Eric Kunze · 2 years, 6 months ago
  76. b79c7d1 Insert missing close bracket in ADD pseudocode by Eric Kunze · 2 years, 6 months ago
  77. 63e7937 Fix spelling mistake in SELECT by Eric Kunze · 2 years, 6 months ago
  78. d15d02d Update specification revision to 0.24.0 draft by Eric Kunze · 2 years, 7 months ago
  79. 8aa23a5 Remove draft tag from 0.23 specification by Eric Kunze · 2 years, 7 months ago v0.23 v0.23.0
  80. 82f19e2 Readability fixes for pseudocode by Eric Kunze · 2 years, 7 months ago
  81. 3fe5256 Clarify CLAMP pseudocode by Eric Kunze · 2 years, 7 months ago
  82. 3170439 Remove zp subtraction from tensor_read pseudocode by Eric Kunze · 2 years, 7 months ago
  83. 82019a2 Remove rank upper limit on TRANSPOSE operator by Eric Kunze · 2 years, 7 months ago
  84. a0266b0 Fix typo int_t to in_t by Eric Kunze · 2 years, 7 months ago
  85. 7c5f532 Add ERROR_IF checks to CONCAT operator by Matthew Haddon · 2 years, 7 months ago
  86. 718ef8e refactor SLICE error_if checks by Matthew Haddon · 2 years, 7 months ago
  87. 7c2cdbc Force output shape to be correct for pooling operations by Matthew Haddon · 2 years, 7 months ago
  88. b6335b8 Move quantization parameters into argument tables by Eric Kunze · 2 years, 8 months ago
  89. c949f8a Allow PAD operator to pad with non-zero by Eric Kunze · 2 years, 8 months ago
  90. d921624 Change TABLE operator table to be an attribute for BI/MI by Eric Kunze · 2 years, 8 months ago
  91. b37e7fb Don't allow pooling ops with excessive padding by Eric Kunze · 2 years, 8 months ago
  92. f1b531a CAST: Correct profile for floating point casts by Dominic Symes · 2 years, 8 months ago
  93. 173fc16 Clarify range limitations for tensors by Eric Kunze · 2 years, 9 months ago
  94. 32de391 MAX_POOL2D: Fix padding behaviour by Dominic Symes · 2 years, 9 months ago
  95. 8f57f9e Fix pooling argument tables by Eric Kunze · 2 years, 9 months ago
  96. ca2a854 Add definition of TOSA compliance by Dominic Symes · 3 years, 2 months ago
  97. a910153 Replace assert with REQUIRE() by Eric Kunze · 3 years ago
  98. f19e594 RESIZE: Clarify dimension limits by Dominic Symes · 3 years ago
  99. 7a2e08c Rename and clarify the divide operator. by Dominic Symes · 3 years ago
  100. ed1b5a9 Removed IDENTITYN and PLACEHOLDER by Suraj Sudhir · 3 years ago