Google Git Google Git
Sign in
android/platform/external/executorch/HEAD
  1. 28d3bc0 Update executorch library to support training am: 2f6652186e by Qiao Li · 1 year, 9 months ago main
  2. 2f66521 Update executorch library to support training by Qiao Li · 1 year, 9 months ago
  3. d9f830b Empty merge ab/12770256 into aosp-main-future by Xin Li · 1 year, 10 months ago
  4. 3815a45 Add janitors to the OWNERS file am: fbe97e7dae by Sadaf Ebrahimi · 1 year, 10 months ago
  5. fbe97e7 Add janitors to the OWNERS file by Sadaf Ebrahimi · 1 year, 11 months ago
  6. 1c57f81 Merge "Revert^2 "Add build targets for JNI and java library"" into main am: 8bd67a6a94 by Treehugger Robot · 1 year, 11 months ago
  7. 8bd67a6 Merge "Revert^2 "Add build targets for JNI and java library"" into main by Treehugger Robot · 1 year, 11 months ago
  8. e0c1d89 Revert^2 "Add build targets for JNI and java library" by Qiao Li · 1 year, 11 months ago
  9. 4665f53 Merge "Revert "Add build targets for JNI and java library"" into main am: 51026adef4 by Liana Kazanova · 1 year, 11 months ago
  10. 51026ad Merge "Revert "Add build targets for JNI and java library"" into main by Liana Kazanova · 1 year, 11 months ago
  11. c57d612 Revert "Add build targets for JNI and java library" by Liana Kazanova · 1 year, 11 months ago
  12. e518cad Merge "Add build targets for JNI and java library" into main am: 92c907466e by Qiao Li · 1 year, 11 months ago
  13. 92c9074 Merge "Add build targets for JNI and java library" into main by Qiao Li · 1 year, 11 months ago
  14. 7c6a4d1 Add build targets for JNI and java library by Qiao Li · 1 year, 11 months ago
  15. e42d645 Upgrade executorch to 91afa6e9234711ad76452f6bad192efe626dcabb am: 3d47424bdf am: f1736f9e19 by Qiao Li · 2 years ago aml_cbr_351410000 aml_ips_351410000 aml_net_351410000 aml_net_351410060 aml_per_351410020 aml_wif_351410040
  16. f1736f9 Upgrade executorch to 91afa6e9234711ad76452f6bad192efe626dcabb am: 3d47424bdf by Qiao Li · 2 years ago
  17. 3d47424 Upgrade executorch to 91afa6e9234711ad76452f6bad192efe626dcabb by Qiao Li · 2 years ago
  18. 91afa6e Fix type-safety of `torch.nn.Module` instances by Edward Z. Yang · 2 years ago
  19. 96a9d35 Qualcomm AI Engine Direct - Optimize memory usage at runtime (#7003) by shewu-quic · 2 years ago
  20. 2c65b97 Take advantage of C++17 in scalar_type_util.h (#7022) by pytorchbot · 2 years ago
  21. 8d71cd3 [llama-mm] Make text decoder exportable (#6999) by Mengwei Liu · 2 years ago
  22. 2adb1bc [Android] Remove runtime internal evalue list types (#7012) by Hansong · 2 years ago
  23. 4e90293 Update CONTRIBUTING.md to reflect "Squash and merge" option (#5117) by Hansong · 2 years ago
  24. 6ac19cc Java Tensor and EValue serialization (#6620) by Hansong · 2 years ago
  25. 7375cf5 Fix _native_batch_norm_legit_no_stats_out by Manuel Candales · 2 years ago
  26. 0070680 add Qualcomm SA8295 support (#6986) by tianxf99 · 2 years ago
  27. 3a35889 Minor perf improvements to quantized linear 8 bit shader. by trivedivivek · 2 years ago
  28. ce77995 Updating add operator with name space changes (#6433) by dijopaul · 2 years ago
  29. 270d055 Arm backend: Make run.sh handle portable ops using aten::<OP>.<modifier>out by Zingo Andersen · 2 years ago
  30. 08ed54e Add pytest option to run FVPs in fast mode by Erik Lundell · 2 years ago
  31. 43555d2 Add mobilenet_v2 and resnet50 to the examples by mcremon-meta · 2 years ago
  32. 50b4ac3 Add buck build for static llama runner by cccclai · 2 years ago
  33. aa8d904 Use getops to pass flags and arguments for test_llama.sh by cccclai · 2 years ago
  34. a39ea29 add remove ops to oss and callsites, [cadence][8/X] add reorder ops to oss and callsites, [cadence][9/X] add replace ops to oss and callsites, [cadence][10/X] merge passes with replace remove ops passes and update default pass order... by JP · 2 years ago
  35. 792ef43 [ET-VK] Move `save_cache` from Runtime dtor to model destroy (#7002) by pytorchbot · 2 years ago
  36. 0dc25e5 [ET-VK] Only save_cache the first time (#7001) by pytorchbot · 2 years ago
  37. 6b0bb56 [ET-VK] Remove unneeded `Runtime` move (#7000) by pytorchbot · 2 years ago
  38. e721945 Clear out Dynamo cache in between tests by Animesh Jain · 2 years ago
  39. b132c96 Enable bool type for _local_scalar_dense (#6994) by Jack Zhang · 2 years ago
  40. a93e716 Add exported program runner (#6969) by Jack Zhang · 2 years ago
  41. 711f1c2 Simplify Xcode configs. by Anthony Shoumikhin · 2 years ago
  42. bafae87 Use GitHub mirrors of mlplatform submodules to unbreak ExecuTorch CI (#6991) by pytorchbot · 2 years ago
  43. 359e9d3 Fix custom annotation (#6978) by cccclai · 2 years ago
  44. 84222a9 Update apple-runtime.md (#6985) by Anthony Shoumikhin · 2 years ago
  45. dcacde0 Update docs on linkage and debugging. by Anthony Shoumikhin · 2 years ago
  46. 709e739 Qualcomm AI Engine Direct - Optimization in static llama by shewu-quic · 2 years ago
  47. af87283 add simply ops to oss, update fuse simply callsites by JP · 2 years ago
  48. f40daea Fix ARM submodule URLs (#6973) by Scott Wolchok · 2 years ago
  49. 54feeef add uint16 to serialization by Jacob Szwejbka · 2 years ago
  50. 1de96f8 Move the rest qnn model jobs to the new qnn sdk docker by cccclai · 2 years ago
  51. 809a1a5 Fix pyre by Hansong · 2 years ago
  52. 34d4398 split to_cadence_edge_executorch API to to_cadence and to_executorch_gen_etrecord by JP · 2 years ago
  53. 8470cb9 import test graph builder to oss, import im2row by JP · 2 years ago
  54. 97cb892 add graph builder in oss for fuse ops by JP · 2 years ago
  55. fbc384c Lower confidence threshold in tests to avoid flakiness. by Anthony Shoumikhin · 2 years ago
  56. f477fd5 Label checker fix (#6953) by Jack Zhang · 2 years ago
  57. eae0b04 add fuse ops passes in oss by JP · 2 years ago
  58. 86cb5d7 Fix error message. by Hardik Sharma · 2 years ago
  59. 04f6fcd Fix ReLU fusion when conv/linear has > 1 user by Max Ren · 2 years ago
  60. 8cce45b Add PR release note label checker bot (#6835) by Jack Zhang · 2 years ago
  61. 85fca59 Add documentation (#6883) by neuropilot-captain · 2 years ago
  62. a0ac820 update OSS pre-existing passes and migrate callsites to OSS by JP · 2 years ago
  63. 7bfe3b9 Fix Cuda out of memory issue for eager runner (#6935) by pytorchbot · 2 years ago
  64. 8013822 Strip local file paths from builds. by Anthony Shoumikhin · 2 years ago
  65. 7278519 update sccache to latest version (#6837) by Wouter Devriendt · 2 years ago
  66. f145ced Port memory planning to Cadence by skrtskrtfb · 2 years ago
  67. 88df185 Fix erroneous `extension_features` initialization by Sicheng Stephen Jia · 2 years ago
  68. 4086509 Dev weight sharing by haowhsu-quic · 2 years ago
  69. 76a0e0f Introduce static targets by Sicheng Stephen Jia · 2 years ago
  70. ee74d06 remove codegen-nosub from q_8w by Nathanael See · 2 years ago
  71. 5b4d9bb [Executorch] optimized sigmoid by Hansong · 2 years ago
  72. c242a59 [Executorch][Portable] Dont upcast to double for sigmoid by Hansong · 2 years ago
  73. 3b475e3 [llama-mm] Fix AOTI test for attention (#6915) by Mengwei Liu · 2 years ago
  74. 4f9ae32 [llama-mm] Reduce copies in SDPA in MHA (#6917) by Mengwei Liu · 2 years ago
  75. 3784f06 Add MobileNetV2Evaluator to Arm Backend by Tom Allsop · 2 years ago
  76. 8526d0a Arm backend: Set default allocation pool to 20MB by Zingo Andersen · 2 years ago
  77. e95f171 Qualcomm AI Engine Direct - Quantizer refine for qat by Chun-I Tsai · 2 years ago
  78. 19268de Introduce data schema to store raw tensors (#6919) by lucylq · 2 years ago
  79. 793a988 Fix arm dependency by lucylq · 2 years ago
  80. d5f91bf Temporarily disable OOMing llama vision decoder test (#6908) by Jack Zhang · 2 years ago
  81. 0692ef4 Pyre fix by lucylq · 2 years ago
  82. ca44965 Introduce no_volk buck targets by Sicheng Stephen Jia · 2 years ago
  83. ae61100 Remove assert for ArgSchema by Riley Dulin · 2 years ago
  84. 3813f42 Only use `LINEAR` tiling if it's available by Sicheng Stephen Jia · 2 years ago
  85. fe5caad Move linker flags to config files for clarity. by lucylq · 2 years ago
  86. 5663e3c [MTK] Add support for Llama 3.2 and code updates to align with current ET API for dynamic dim by neuropilot-captain · 2 years ago
  87. c734ad4 Change the branch to download frameworkd from. by Anthony Shoumikhin · 2 years ago
  88. e32d1b7 Simplify .xcoconfig. by Anthony Shoumikhin · 2 years ago
  89. f96be5b Add UInt16 support to Cadence kernels by Riley Dulin · 2 years ago
  90. 0877926 Add UInt16 support to Q and DQ by Jacob Szwejbka · 2 years ago
  91. 92ee522 merge internal op registration with oss by JP · 2 years ago
  92. b4ab76f Remove template file after renaming and amending. (#6885) by Anthony Shoumikhin · 2 years ago
  93. 54899fe Adding tests old lowering flow for op_abs.py by ru-m8 · 2 years ago
  94. 041b7d6 Refactor TOSAOperatorSupport to allow for maping against TosaSpecification by Per Åstrand · 2 years ago
  95. 4a18003 Add TosaSpecification to ArmPartitioner by Per Åstrand · 2 years ago
  96. 04b3d92 [llama-mm] Add torch.cond to replace if condition in MHA (#6869) by Mengwei Liu · 2 years ago
  97. 7b76f0f Make TorchTune Llama model KV cache compatible in eager (#6643) by Jack Zhang · 2 years ago
  98. e384c1a Fix Xcode projects packages pins. by Anthony Shoumikhin · 2 years ago
  99. b386322 Update Xcode projects to use nightly builds. (#6873) by Anthony Shoumikhin · 2 years ago
  100. b0f6048 Fix test_model.sh for vision text decoder (#6874) by Jack Zhang · 2 years ago