Google Git
Sign in
chromium/external/github.com/google-ai-edge/LiteRT/HEAD
  1. 0a03390 Automated Code Change by Google AI Edge · 23 minutes ago upstream/main
  2. 1d3c133 Fix ASSIGN_OR_RETURN clang-tidy warning by Marissa Ikonomidis · 5 hours ago
  3. e6168e7 Merge pull request #8561 from graham0824:dev/chunhsue/graph_config_hooks by Copybara-Service · 6 hours ago
  4. 8079787 Relocate tflite_profile and clean up infra dependencies by Terry Heo · 8 hours ago
  5. 2069beb Relocate shared_memory_manager to delegate/shared_memory_manager by Terry Heo · 9 hours ago
  6. c509b8d PR #121681: Fix SelectV2 abort on broadcasts with output rank >= 6 by San · 9 hours ago
  7. 5e5f623 Copybara import of the project: by destro4evr · 16 hours ago
  8. 4f54610 Copybara import of the project: by destro4evr · 18 hours ago
  9. 62da3dc Fix CPU cache synchronization for DMA-BUF tensor buffers. by Google AI Edge · 20 hours ago
  10. bdaad41 Update `thrInvocationContextDetachBuffer` documentation to explicitly indicate the purpose of the `ThrBufferHandle` parameter. by Google AI Edge · 22 hours ago
  11. cf959e0 Qualcomm AI Engine Direct - Move per-backend graph-config building into QnnBackend. by Chun-Hsueh Lee · 24 hours ago
  12. a19d8fa Merge pull request #8256 from graham0824:dev/chuntl/update_mode_before_execution by Copybara-Service · 24 hours ago
  13. 7f79427 Add LiteRT Objective-C tensor buffer wrapper class by Terry Heo · 25 hours ago
  14. c3390e3 Update LiteRT.js npm package versions to 2.5.3 by Google AI Edge · 27 hours ago
  15. 1745b10 Internal integration of GitHub PR 115950 for TFLite location metadata improvements. by Dmitri Latushko · 27 hours ago
  16. 77ae937 Internal integration of GitHub PR 115950 for TFLite location metadata improvements. by Dmitri Latushko · 27 hours ago
  17. 1193834 Relocate serialization_program_cache to litert/ml_drift/delegate by Terry Heo · 30 hours ago
  18. a14364c Internal Change Only by Google AI Edge · 31 hours ago
  19. ac4e6fc Copy and migrate ml_drift_delegate utilities to ml_drift/delegate by Terry Heo · 33 hours ago
  20. 44c71d8 Support TFLite custom ops in CompiledModel by Terry Heo · 33 hours ago
  21. 260f0c8 Fix sign reference implementation by Dillon Sharlet · 34 hours ago
  22. 61f4324 Force `LockedBufferSpan` data access through an lvalue. by Quentin Khan · 2 days ago chromium/7957
  23. 64b148a Rollback shared/external weights by Google AI Edge · 2 days ago
  24. 3535a6b Fix benchmark model to respect default NPU options if not received in ABSL flags. by Andrew Zhang · 2 days ago
  25. df4d621 Automated Code Change by Google AI Edge · 2 days ago
  26. 8b651bb Broadcom LiteRT update 07152026 ,Add missing cmake files , add a script to build by Google AI Edge · 2 days ago
  27. 21f9733 Add LiteRT Objective-C compilation options class by Terry Heo · 2 days ago
  28. 0ba4b41 Moved serialization_weight_cache to litert/ml_drift/ by Terry Heo · 2 days ago
  29. 3fd1c4c Enable ATS delegate tests for PAD by Google AI Edge · 2 days ago
  30. 4d4947b Update org_tensorflow dependency in litert WORKSPACE. by Changming Sun · 2 days ago
  31. b9491ff Add boundary checks to pad-like kernels by Changming Sun · 2 days ago
  32. e3ef670 Add boundary checks to pad-like kernels by Changming Sun · 2 days ago
  33. 40b4d88 Add LiteRT Objective-C base error and environment APIs by Terry Heo · 2 days ago
  34. cc9aa78 Expose op profiling symbols to litert windows DLL. by Google AI Edge · 2 days ago
  35. d2bf64c Internal changes only by Byungchul Kim · 2 days ago
  36. c7e4b43 Remove unused options now that dawn is dynamically linked by Google AI Edge · 2 days ago
  37. 9558713 Update GPU library path by Terry Heo · 2 days ago
  38. 77e8220 Automated Code Change by Google AI Edge · 2 days ago
  39. 49a42fb Rust Binding documentation update, documented async functionality. by Google AI Edge · 2 days ago
  40. 68c8877 Try keeping buffer and tensor type coherent. by Quentin Khan · 2 days ago
  41. e38ed2f Support static library linking on Windows in LITERT_CAPI_EXPORT by Lynne Jiang · 2 days ago
  42. 67017d1 Fix ambiguous operator== between std::string_view and absl::string_view by Matt Kreileder · 2 days ago
  43. 3bb8b65 Allow passing a scalar value as the `TensorInit` buffer. by Quentin Khan · 3 days ago
  44. 2b6ba8d Qualcomm AI Engine Direct - Enable HTP/DSP power config auto mode. by chuntl-qti · 3 days ago
  45. bd3e3db Internal changes only. by Fengwu Yao · 3 days ago
  46. e5203b0 Support clearing `kLiteRtTensorBufferTypeHostMemory` tensor buffers in `LiteRtTensorBufferT::Clear()`. by Google AI Edge · 3 days ago
  47. 9993fbe Added python binding for the new enable_ynnpack option by Google AI Edge · 3 days ago
  48. 77b2aef Fix quantization export to allow explicit q/ dq nodes in the graph by Google AI Edge · 3 days ago
  49. 2705052 Initial Implementation of Streamed Loading to WebGPU on LiteRT.js (6/6) by Google AI Edge · 3 days ago
  50. 2a77d29 [ir-model] Gracefully fail on int64 by Grant Jensen · 3 days ago
  51. d4b0be6 Initial Implementation of Streamed Loading to WebGPU on LiteRT.js (5/6) by Google AI Edge · 3 days ago
  52. 759f2f0 Reverts changelist 943945332 by Google AI Edge · 3 days ago
  53. d952913 Initial Implementation of Streamed Loading to WebGPU on LiteRT.js (4/6) by Google AI Edge · 3 days ago
  54. 65491d0 Fix IsIsolatedProcess check to account for secondary users by applying modulo 100000 to getuid(). by Daniel Sosa · 3 days ago
  55. 5f8bc47 PR #120403: [oneDNN] Default to oneDNN async execution for x86_64 Linux builds by Om Thakkar · 4 days ago
  56. cc0d407 Add NPU accelerator mode to Gemma3 LiteRT runner by Google AI Edge · 4 days ago
  57. 44806f7 Lower odml composite ops natively instead of inlining by Google AI Edge · 4 days ago
  58. fd107f1 Reverts 241fc1309870f11243ff97473935fe3050468f32 by Google AI Edge · 4 days ago
  59. 29ac81e Automated Code Change by Google AI Edge · 4 days ago
  60. 3a7cf7f Open source litert/runtime/accelerators/gpu/ by Terry Heo · 4 days ago
  61. 7a7b085 Fix TensorRT dispatch buffer rebinding by Google AI Edge · 4 days ago
  62. 241fc13 Add SetResidencyRuntimeEnabled option to GpuBackendMetal. by Fengwu Yao · 4 days ago
  63. ff6d130 Fix presubmit checks about unchecked absl::StatusOr access. by Quentin Khan · 4 days ago
  64. 61b03b8 Add CUDA device buffers to NVIDIA dispatch by Google AI Edge · 4 days ago
  65. 8c293eb Remove obsolete SHLO reference library and experimental StableHLO tests by Terry Heo · 4 days ago
  66. 453b799 Remove obsolete SHLO reference library and experimental StableHLO tests by Terry Heo · 4 days ago
  67. 03b70b4 Add Gemma3 GPU profiling controls by Google AI Edge · 4 days ago
  68. 3b73fc5 Enable gemma3 (authored in tensor API) running on tensor rt using dispatch API by Google AI Edge · 4 days ago
  69. ef27211 Added option to enable ynnpack integration with litert by Google AI Edge · 4 days ago
  70. 11ac389 Fix potential integer overflow and improve safety in evaluation stages. by Dmitri Latushko · 4 days ago
  71. f02d731 Update a reference to the "LiteRT Next" APIs to instead refer to the LiteRT "Compiled Model" APIs. The "LiteRT Next" name has been retired in favour of this new name. by Fergus Henderson · 4 days ago
  72. e6ce8d5 Fix warnings about control reaching the end of a non-void function. by Quentin Khan · 4 days ago
  73. 5c48f2b Lazily create the `Environment` object in `Simplebuffer` by Dillon Sharlet · 4 days ago
  74. 110dc20 Internal changes only. by Google AI Edge · 4 days ago
  75. b468ed4 Implement conversion over ranges of elements. by Quentin Khan · 5 days ago
  76. 1566174 Add equality operator to int4_t and int2_t. by Quentin Khan · 5 days ago
  77. 129aa82 Revert default FlatBuffer verification in BuildFromAllocation to resolve memory regression, using lightweight offset validation instead. by Dmitri Latushko · 5 days ago
  78. ff4eeaa Revert default FlatBuffer verification in BuildFromAllocation to resolve memory regression, using lightweight offset validation instead. by Dmitri Latushko · 5 days ago
  79. d8040ef Allow high-rank StridedSlice by Google AI Edge · 6 days ago
  80. 464ea1e Allow high-rank Slice by Google AI Edge · 6 days ago
  81. 9011640 Allow null tensor buffer destroy by Google AI Edge · 7 days ago
  82. 5724bf4 Added ynnpack accelerator by Google AI Edge · 7 days ago
  83. 2911db7 Fix QC compiler doc. by Andrew Zhang · 7 days ago
  84. 2289909 Move thread pool from YNNPackDelegateKernel to YNNPackDelegate by Dillon Sharlet · 7 days ago
  85. 4b805d1 Fix IrModel special selector wiring and add overloads for IrModelToGpuModel for w/ a custom OpSelector by Grant Jensen · 7 days ago
  86. 4bce445 Internal auto cleanup applied. by Ricardo Torres · 7 days ago
  87. 2903255 Enable CPU-only build without GPU dependencies by Salil Tambe · 7 days ago
  88. 18b9c86 Update Tensorflow version to update XNNPack version. by Misha Gutman · 7 days ago
  89. 44024c5 Support SK_CODEC_DECODES_PNG_WITH_RUST in skia_image_preprocessor for Chromium / Rust PNG compatibility by Google AI Edge · 7 days ago
  90. 0b0d663 Fix potential OS command injection in MLIR conversion utility. by Ricardo Torres · 7 days ago
  91. e2404b4 Expose LiteRT GPU Accelerator by Terry Heo · 7 days ago
  92. 9059165 Includes signature name in benchmark results by David Massoud · 7 days ago
  93. f51aa89 Fix allocation behaviour in OwningCpuBuffer::(Copy|Transform). by Quentin Khan · 7 days ago
  94. 252ac7a Merge pull request #8175 from graham0824:dev/mingxiup/fix_pack_test_floatnear by Copybara-Service · 7 days ago
  95. 7c67be4 Suppress linter warning for TensorHandle error status implicit construction. by Quentin Khan · 8 days ago
  96. 448ff40 Updated XNNPACK version. by Misha Gutman · 8 days ago
  97. 445ba77 Merge pull request #8389 from Jiseong-oh:update_img_prepros by Copybara-Service · 8 days ago
  98. 70fcc5d Merge pull request #8538 from graham0824:dev/chunhsue/clean_deps by Copybara-Service · 8 days ago
  99. 8c790cc Merge pull request #8150 from graham0824:dev/jiunkaiy/enable_a8w2 by Copybara-Service · 8 days ago
  100. 4699995 Automated Code Change by Google AI Edge · 8 days ago