Google Git
Sign in
chromium/external/github.com/google-ai-edge/LiteRT/HEAD
  1. cad0125 Release bytecode-only compiler results after model copy by Google AI Edge · 61 minutes ago upstream/main
  2. 2b957c6 Add profiling support for Metal backend in LiteRT delegate by Marissa Ikonomidis · 82 minutes ago
  3. 35c00f8 Fix SIGSEGV in Validator destructor by reordering members. by Alexandru Paiu · 2 hours ago
  4. 4abff8e Fix Samsung NPU CMake build by using local headers if available. by Alexandru Paiu · 6 hours ago
  5. 1a9b533 Merge pull request #8745 from anikulk:weight_sharing_ovgpu by Copybara-Service · 27 hours ago
  6. 7720d97 Refactor TFLite cast kernel saturating cast helper by Changming Sun · 2 days ago
  7. 289b1ba Implement delegate-driven early inlining for YNNPACK by Dillon Sharlet · 3 days ago
  8. 5cc6662 Update Intel OpenVINO compiler dependencies in LiteRT by Chunlei Niu · 3 days ago
  9. 13f9d10 Grant internal package visibility to third_party/ai_lab. by Fenghui Zhang · 3 days ago
  10. 91ce8cf Add bound check to TFLite reshape kernel output shape calculation by Changming Sun · 3 days ago
  11. 42d3d65 Drop more usage of dynamic_runtime targets. by Chunlei Niu · 3 days ago
  12. a9b8a80 Fix LiteRT profiler for delegate kernel nodes by Terry Heo · 3 days ago
  13. cb2d1e8 Fix TCMalloc crash in LiteRtGetProfileSummary by Terry Heo · 3 days ago
  14. de07341 Reverts ed05dea6e92d60f61dd5c0c0f7b4aa268b448165 by Google AI Edge · 3 days ago
  15. 7c4edf7 Make it possible to map buffer identifiers manually. by Quentin Khan · 3 days ago
  16. 6e66398 Copybara import of the project: by destro4evr · 3 days ago
  17. fb91408 Add integer overflow checks to TFLite convolution kernels by Changming Sun · 4 days ago
  18. 82655e4 Add cast_bf16_to_fp32 cast pass by Majid Dadashi · 4 days ago
  19. ed05dea Add flag to switch LiteRT to use IrModel over GraphFloat32 by Grant Jensen · 4 days ago
  20. fbec119 [ir-model] Implement Blockwise quantization schema to IrModel -- achieving parity w/ GF32 quantization schemas by Grant Jensen · 4 days ago
  21. f92f139 Fix pytype protocol signatures and parameter annotations in model_utils and algorithm_manager_api by Majid Dadashi · 4 days ago
  22. 618f9aa [Intel OV] Enable weight-sharing tests in Windows CI by Anisha Kulkarni · 4 days ago
  23. a5a3dfa [Intel OV] Ensure per-model bank, name-keyed const_map, version byte by Anisha Kulkarni · 4 days ago
  24. 45bce10 [Intel OV] Dispatch: GlobalGraph weight sharing (GPU) by Anisha Kulkarni · 4 days ago
  25. bc1d0c1 [Intel OV] Wire up cross-partition weight sharing (GPU) by Anisha Kulkarni · 4 days ago
  26. e00c73c [Intel OV] Add weights-to-parameters transform (GPU) by Anisha Kulkarni · 4 days ago
  27. 936825b Add WeightBank class for cross-partition weight sharing by Anisha Kulkarni · 4 days ago
  28. 5751d6c Reverts 0f95035c4a6370b7cbd7f1ebf65cd352af57f1e2 by Matt Kreileder · 4 days ago
  29. b2b614f Upstream support for PFFFT audio preprocessor implementation. by Google AI Edge · 4 days ago
  30. 459ff0e Added XNNPACK RMSnorm to transformer_ops. by Misha Gutman · 4 days ago
  31. 202b35b Fix open-source WebGPU and OpenCL accelerator builds for Linux and Android by Terry Heo · 4 days ago
  32. 365e885 Merge pull request #8910 from abc21086999:fix/ml-dtypes-base-dependency by Copybara-Service · 4 days ago
  33. cb4940b Improve stale cache test for XNNPack weight cache. by Quentin Khan · 4 days ago
  34. b98a92a Normalize GPU models (renderer) for Samsung Xclipse, PowerVR, and VirtIO Venus to ensure consistency across OS updates and driver versions. by Google AI Edge · 5 days ago
  35. cd3839b This is an internal change. by Chunlei Niu · 5 days ago
  36. 0f95035 Fix lock leaks and self-deadlock in LiteRT NPU runtime. by Salil Tambe · 5 days ago
  37. e1d9941 Fix CWE-697 transitivity violation in TopK comparator when NaN is present by Changming Sun · 5 days ago
  38. 4cbb9ed Revert a debug only check in NumElements by Changming Sun · 5 days ago
  39. f52d08b Fix typo in ABSL_ASSERT_OK test utility macro. by Google AI Edge · 5 days ago
  40. 8fd0b9c Add multi-signature support to ObjC LRTCompiledModel by Terry Heo · 5 days ago
  41. 6705c5a [ir-model] Shared quantized weights are no longer forced to be dequant in 1x1 fc/conv ops. by Grant Jensen · 5 days ago
  42. 82272d2 Keep graph agnostic functions of SMM in place: move graph dependent fcns to virtual graph adapter which can be overridden by either IrModel or GF32. by Grant Jensen · 5 days ago
  43. 8119eb7 internal changes only by Changming Sun · 5 days ago
  44. a0b393e Improve null safety in TFLite and MLIR FlatBuffer conversions for optional StableHLO Gather dimension parameter vectors. by Qidong Zhao · 5 days ago
  45. ca485df Improve null safety in TFLite and MLIR FlatBuffer conversions for optional StableHLO Gather dimension parameter vectors. by Qidong Zhao · 5 days ago
  46. 717f56c Internal changes only. by Fengwu Yao · 5 days ago
  47. 9ea3844 Merge pull request #8442 from graham0824:dev/weilhuan/preset_toolchain by Copybara-Service · 6 days ago
  48. da7639c Merge pull request #8921 from graham0824:dev/chunhsue/dlc_test by Copybara-Service · 6 days ago
  49. 7e36680 Harden reduce-family TFLite kernels by Changming Sun · 6 days ago
  50. 17c6496 Automated Code Change by Google AI Edge · 6 days ago
  51. 418c7da Add a drop shape assertion pass by Majid Dadashi · 6 days ago
  52. b65d712 Add ABSL_ASSERT_OK() macro as it's preferred to ASSERT_OK by Byungchul Kim · 6 days ago
  53. 1d031f6 Samsung Exynos AI LiteCore: add samsung backend in init by Jiseong-oh · 6 days ago
  54. 3cb830a Update Dawn to v20260720.160313 and use modern WebGPU cache callbacks by Terry Heo · 6 days ago
  55. 2602c8a Refactor streaming detokenization using BufferedStreamingDetokenizer. by Mohammadreza Heydary · 6 days ago
  56. 94342f7 Add Dequantize support to the XNNPack backend. by Quentin Khan · 6 days ago
  57. b043614 Add more detailed comments for SetSharedTensorMaps GPU option by Byungchul Kim · 6 days ago
  58. 4c0ea3d Update litert/cc/CMakeLists.txt to avoid pulling in absl dependencies by Google AI Edge · 7 days ago
  59. 3508ca9 Updated source_build_cc_api_run_model.cc to include the newly declared data types by Google AI Edge · 7 days ago
  60. cd3d961 Clean up absl symbols from public cc APIs by Google AI Edge · 7 days ago
  61. 81be779 This is an internal change by Google AI Edge · 7 days ago
  62. 558d564 Remove grte dependency from Tensor API's litert_main by Google AI Edge · 7 days ago
  63. 47e155f Upgrade pack/slice/reshape op shape inferrer to the stateless interface. by Andrew Zhang · 7 days ago
  64. d53e0e1 Merge pull request #8709 from graham0824:dev/mingxiup/space_batch_nd_op by Copybara-Service · 7 days ago
  65. b1c33e9 Change default setting of YNNPACK options in LiteRT-LM by Dillon Sharlet · 7 days ago
  66. 7c94d25 Merge pull request #8821 from graham0824:dev/jiunkaiy/simple_soc_table by Copybara-Service · 7 days ago
  67. 1911faf Fix signature tensor type lookups by Google AI Edge · 7 days ago
  68. 5997fc1 Qualcomm AI Engine Direct - Add DLC test. by Chun-Hsueh Lee · 7 days ago
  69. 9eedac0 Fix google tensor compiler plugin tests by Andrew Zhang · 7 days ago chromium/7979 chromium/7980 chromium/7981 chromium/7982 chromium/7983 chromium/7984 chromium/7985 chromium/7986 chromium/7987 chromium/7988 chromium/7989
  70. 0712c67 Merge pull request #8871 from graham0824:dev/jiunkaiy/fix_dlc by Copybara-Service · 7 days ago
  71. 62b1cdd Merge pull request #8865 from graham0824:dev/chuntl/fix_dlc_qnn_doc by Copybara-Service · 7 days ago
  72. 3d443a1 Implement executable caching by (fd, offset, size) tuples in Google Tensor dispatch. by Google AI Edge · 7 days ago
  73. f4a32da Constrain tfl.dynamic_update_slice folder to not fold when it's connected to module input and output. by Weiyi Wang · 7 days ago
  74. 564722c LiteRT: Fix topological sort in outliner and add regression tests by Andrew Zhang · 7 days ago
  75. bb30867 Specify runfiles in _cc_import_files_impl. by Andrew Zhang · 7 days ago
  76. 339641c Re-add BF16 support to Transpose and DynamicUpdateSlice TFLite ops. by Google AI Edge · 7 days ago
  77. 875a6a0 Add support for external WebGPU instance and flush callback in LiteRT. by Lynne Jiang · 7 days ago
  78. 251db78 Add tooling for building a litert model from npu bytecode. by Andrew Zhang · 7 days ago
  79. 20cfc33 Update boundary checks for memory mapped files by Marissa Ikonomidis · 7 days ago
  80. ff9d2fb open source TFLite testing/fuzzing by Changming Sun · 7 days ago
  81. b0220ab Add mix precision support to litert C API by Changming Sun · 7 days ago
  82. 5b1dcd3 Internal changes only. by Google AI Edge · 7 days ago
  83. baea1d9 PR #119744: Fix ResizeNearestNeighbor reference offset overflow by 0xASTRA · 7 days ago
  84. 7c54bfe Extend RoPE custom op by Google AI Edge · 7 days ago
  85. f536a84 PR #116190: [TFLite] Fix FuseUnpackAndConcatToReshape incorrectly fusing permutations as reshape by SamareshSingh · 7 days ago
  86. f584b34 Increase link memory for TFLite Python tests to fix CPPLink OOM. by Google AI Edge · 8 days ago
  87. df6c9f5 Move ml_dtypes from model-utils extra to base dependency by abc21086999 · 8 days ago
  88. 4b7b429 Add global positive-dimension shape product validation to TFLite verifier. by Changming Sun · 9 days ago
  89. 1921f3d Automated Code Change by Google AI Edge · 10 days ago
  90. 01b4187 Update prebuilt binaries of LiteRT by Terry Heo · 10 days ago
  91. 228c380 Add end-to-end Objective-C integration tests for LiteRT by Terry Heo · 10 days ago
  92. 5ab91f8 Implement event methods to return NOT_FOUND instead of UNIMPLEMENTED in OpenGL by Byungchul Kim · 10 days ago
  93. 629b1b4 Automated Code Change by Google AI Edge · 10 days ago
  94. 7f605f6 Add sub-channel quantization verifiers to TFLite Reshape and Transpose ops. by Vamsi Manchala · 10 days ago
  95. 7345c02 Use `YNN_VALUE_FLAG_COPY_DATA_FP32` to convert types in the YNNPACK delegate by Dillon Sharlet · 10 days ago
  96. c02b3c9 Add CMake build support for LiteRT support libraries. by Google AI Edge · 10 days ago
  97. ca8935c [LiteRT] Remove model graph mutations when compiler plugin compilation fails. by Google AI Edge · 10 days ago
  98. 498727c Reorder operations of ml_drift_delegate. by Byungchul Kim · 10 days ago
  99. eee62a0 Copybara import of the project: by destro4evr · 10 days ago
  100. b628a29 Fix memory leaks in `CreateOpenVinoTensorBuffer` on allocation failure. by Tommy Chiang · 11 days ago