Google Git
Sign in
chromium/external/github.com/google-ai-edge/LiteRT/HEAD
  1. d8040ef Allow high-rank StridedSlice by Google AI Edge · 17 hours ago upstream/main
  2. 464ea1e Allow high-rank Slice by Google AI Edge · 18 hours ago
  3. 9011640 Allow null tensor buffer destroy by Google AI Edge · 2 days ago
  4. 5724bf4 Added ynnpack accelerator by Google AI Edge · 2 days ago
  5. 2911db7 Fix QC compiler doc. by Andrew Zhang · 2 days ago
  6. 2289909 Move thread pool from YNNPackDelegateKernel to YNNPackDelegate by Dillon Sharlet · 2 days ago
  7. 4b805d1 Fix IrModel special selector wiring and add overloads for IrModelToGpuModel for w/ a custom OpSelector by Grant Jensen · 2 days ago
  8. 4bce445 Internal auto cleanup applied. by Ricardo Torres · 2 days ago
  9. 2903255 Enable CPU-only build without GPU dependencies by Salil Tambe · 2 days ago
  10. 18b9c86 Update Tensorflow version to update XNNPack version. by Misha Gutman · 2 days ago
  11. 44024c5 Support SK_CODEC_DECODES_PNG_WITH_RUST in skia_image_preprocessor for Chromium / Rust PNG compatibility by Google AI Edge · 2 days ago
  12. 0b0d663 Fix potential OS command injection in MLIR conversion utility. by Ricardo Torres · 2 days ago
  13. e2404b4 Expose LiteRT GPU Accelerator by Terry Heo · 2 days ago
  14. 9059165 Includes signature name in benchmark results by David Massoud · 2 days ago
  15. f51aa89 Fix allocation behaviour in OwningCpuBuffer::(Copy|Transform). by Quentin Khan · 2 days ago
  16. 252ac7a Merge pull request #8175 from graham0824:dev/mingxiup/fix_pack_test_floatnear by Copybara-Service · 2 days ago
  17. 7c67be4 Suppress linter warning for TensorHandle error status implicit construction. by Quentin Khan · 2 days ago
  18. 448ff40 Updated XNNPACK version. by Misha Gutman · 2 days ago
  19. 445ba77 Merge pull request #8389 from Jiseong-oh:update_img_prepros by Copybara-Service · 2 days ago
  20. 70fcc5d Merge pull request #8538 from graham0824:dev/chunhsue/clean_deps by Copybara-Service · 3 days ago
  21. 8c790cc Merge pull request #8150 from graham0824:dev/jiunkaiy/enable_a8w2 by Copybara-Service · 3 days ago
  22. 4699995 Automated Code Change by Google AI Edge · 3 days ago
  23. 89450e8 Fix type of bias in FullyConnected ATS tests and quantization scale by Dillon Sharlet · 3 days ago
  24. 12750f8 Merge pull request #8114 from neuropilot-captain:260616_upstream by Copybara-Service · 3 days ago
  25. c7738ee Allow moe custom op from LiteRT by Google AI Edge · 3 days ago
  26. fe04ae2 Merge pull request #7932 from graham0824:dev/chuntl/enhance_log by Copybara-Service · 3 days ago
  27. 4157b6f Enable qualcomm core test cases. by Andrew Zhang · 3 days ago
  28. 02d94ad Expose underlying compiled_model from runner for advanced clients by Byungchul Kim · 3 days ago
  29. daf5a95 Includes subgraph name in delegation log message by David Massoud · 3 days ago
  30. 8463101 Merge pull request #8582 from google-ai-edge/litert_pr_945165724 by Matt · 3 days ago
  31. d846569 Check google to github sync workflow by Matt Kreileder · 3 days ago
  32. da3f501 [0/N] fp16 support in tfl schema by Weiyi Wang · 3 days ago
  33. f5d5857 Implement relu_0_to_1 in the YNNPACK delegate by Dillon Sharlet · 3 days ago
  34. b675e39 Add missing ABSL_CONST_INIT to variable definitions by Jesse Rosenstock · 3 days ago
  35. de92b22 Automated Code Change by Google AI Edge · 3 days ago
  36. 7ca8c9b Automated Code Change by Google AI Edge · 3 days ago
  37. 71eca50 Fix `IsQuantized` to return false if the type is not quantized by Dillon Sharlet · 4 days ago
  38. 3751885 Allow per-channel quantization for biases in YNNPACK delegate by Dillon Sharlet · 4 days ago
  39. 2ed0d9e Float16 LiteRT XNNPACK delegate for static pad by Google AI Edge · 4 days ago
  40. 237f253 Enforce that the 1D `size` operand (operand 1) for `ResizeBilinear` and `ResizeNearestNeighbor` TFLite ops is dynamic or has dimension length 2 (`[height, width]`). by Changming Sun · 4 days ago
  41. e750ca2 Internal fix for integer overflow in broadcasting. by Ricardo Torres · 4 days ago
  42. a278d87 Fix integer overflows in SSE 4-bit fully connected kernel array shape computations. by Ricardo Torres · 4 days ago
  43. bbf1cb2 Add missing Apache license headers to MLIR files by Antonio Sanchez · 4 days ago
  44. 5568668 Float16 LiteRT XNNPACK delegate by Google AI Edge · 4 days ago
  45. b8aed30 PR #116205: Validate size tensor element count in resize_bilinear by Tristan · 4 days ago
  46. ba3dc71 Enable 2- and 4-bit types in the YNNPACK delegate by Dillon Sharlet · 4 days ago
  47. fc89a2d Fix STABLEHLO case and scatter tests with delegate support by Dillon Sharlet · 4 days ago
  48. 08e09bf Qualcomm AI Engine Direct - Clean dependencies and format. by Chun-Hsueh Lee · 4 days ago
  49. 0d420cd Float16 LiteRT XNNPACK delegate by Google AI Edge · 5 days ago
  50. d419a5d PR #108244: Fix softmax kernel to zero out invalid channels in output by int-smart · 5 days ago chromium/7940 chromium/7941 chromium/7942 chromium/7943 chromium/7944 chromium/7945 chromium/7946
  51. e7e3eda Add missing license headers. by Antonio Sanchez · 6 days ago
  52. 01d488c Add missing license headers. by Antonio Sanchez · 6 days ago
  53. dd08adb XNNPACK Float16 delegate for SOFTMAX by Google AI Edge · 6 days ago
  54. da5c4aa Automated Code Change by Google AI Edge · 9 days ago
  55. 2be31bc Automated Code Change by Google AI Edge · 11 days ago
  56. e1d2d0e Update XNNPack commit pin and SHA256 by Changming Sun · 11 days ago
  57. 6a0ee2a Propagate GetDims error status in CoreML delegate kernel to prevent uninitialized stack variable usage. by Dmitri Latushko · 11 days ago
  58. 802fe6d Fix heap OOB read and arena corruption in TFLite evaluation stages by validating raw image size and securely copying input data. by Dmitri Latushko · 11 days ago
  59. ed97746 Fix overloaded operator== ambiguity when comparing flatbuffers::String string views with absl::string_view under NDK builds. by Dmitri Latushko · 11 days ago
  60. cb81544 Fix flexbuffers vector creation bug in MLIR TFLite export by Google AI Edge · 11 days ago
  61. d9ca6ef Refactor CheckedShapeProduct to use std::initializer_list. by Esun Kim · 11 days ago
  62. 0dbedd3 Materialize MultiAxisQuantization through interpreter builder by Google AI Edge · 12 days ago
  63. c19a0c7 Automated Code Change by Google AI Edge · 12 days ago
  64. 090c9ad Verify FlexBuffers parsing and use natively tracked lengths in signature defs parsing to prevent out-of-bounds reads. by Dmitri Latushko · 12 days ago
  65. d7a41c7 Disable buffer reuse for stateful ops AssignVariableOp, TensorArrayWriteV3, and QueueEnqueueV2 in Flex delegate to prevent Use-After-Free. by Dmitri Latushko · 12 days ago
  66. f5ed543 Fix missing nullptr checks from BuildTfLiteTensor in list kernels. by Dmitri Latushko · 12 days ago
  67. ec5839e Fix unverified FlatBuffer parsing in strip_buffers. by Dmitri Latushko · 12 days ago
  68. 76eb932 Sync max operator versions in BuiltinRefOpResolver with BuiltinOpResolver. by Esun Kim · 12 days ago
  69. 89fb366 Fix out-of-bounds write in SimpleOp::Invoke. by Dmitri Latushko · 12 days ago
  70. 77fdb57 Fix [[nodiscard]] build error in CreateInputTensorData by using if constexpr and constructing std::complex properly. by Google AI Edge · 12 days ago
  71. 918c9ca Add dependency on delegate to combined kernel tests by Dillon Sharlet · 13 days ago
  72. 1c88f9b Serialize StableHLO composite decompositions by Google AI Edge · 13 days ago
  73. 91f24bc Remove litert_link_capi_so as it's deprecated by Byungchul Kim · 13 days ago
  74. 7587e74 Add api_visibility.bzl to control API visiblity by Terry Heo · 13 days ago
  75. 1cae4d3 Automated Code Change by Google AI Edge · 13 days ago
  76. 9c2bf3d Add JIT caching to Kotlin API. by Andrew Zhang · 13 days ago
  77. 78ce760 Add StableHLO composite TFLite options by Google AI Edge · 13 days ago
  78. 7c845c6 Internal changes only by Byungchul Kim · 13 days ago
  79. 3647910 flatbuffer change for experimental usage by Weiyi Wang · 13 days ago
  80. 005989b Fix heap buffer overflow in StableHLO Pad due to unchecked tensor rank and downcasts. by Dmitri Latushko · 13 days ago
  81. 76e78b3 External weights from host heap memory by Byungchul Kim · 13 days ago
  82. 03589b1 Add tensor StableHLO composite API using lambda by Google AI Edge · 13 days ago
  83. 68a4a70 This is an internal change by Google AI Edge · 13 days ago
  84. 07e4761 Add bounds checks in TOCO ResolveConstantPack before memcpy to prevent heap buffer overflow and out-of-bounds read. by Dmitri Latushko · 13 days ago
  85. 377ca31 Reverts 3474cd9da4fa9c95a01049ae7f12d3c91f4bb8e0 by Chunlei Niu · 13 days ago
  86. 622f1f3 Implement ExtractLocalCache for ML Drift and refactor Gemma3 attention. by Ping Yu · 13 days ago
  87. 1461b6b Cleanup C API dependency of GoogleTensor Compiler by Terry Heo · 13 days ago upstream/2.1.6 upstream/v2.1.6
  88. 27382db lite: Fix memory leak in GPU delegates by Google AI Edge · 13 days ago
  89. 3820561 Fix LiteRT windows build error. by Jun Jiang · 13 days ago
  90. 0e535ad Add support for quantize, dequantize, more activations to YNNPACK delegate by Dillon Sharlet · 13 days ago
  91. 34e635c Show unittest errors in workflow console by Byungchul Kim · 13 days ago
  92. c852b8f No public description by Weiyi Wang · 13 days ago
  93. 70ddd5b Fix LiteRT Python wrapper crash under Python 3.14 by Matej Aleksandrov · 13 days ago
  94. fd36a10 PR #115190: Fix int16x8 quantization for SQRT op in TFLite by SamareshSingh · 13 days ago
  95. 0988ea0 Update Image Preprocessor by jiseong oh · 13 days ago
  96. 26e90cd Qualcomm AI Engine Direct - Use FloatNear in Pack and SplitV test. by Ming-Hsiu Pan · 13 days ago
  97. f84c054 Fix potential index out-of-bounds or divide by zero errors. by Google AI Edge · 13 days ago
  98. 4117a56 Add YNNPACK delegate by Dillon Sharlet · 14 days ago
  99. ae92c6b internal change to a library by David Massoud · 2 weeks ago
  100. 2321736 Implement batched decode for Gemma3 on ML Drift. by Ping Yu · 2 weeks ago