Google Git
Sign in
chromium / external / github.com / tensorflow / tensorflow / HEAD
  1. d97b0d4 Separate stacks for python frames and c frames. by Clive Verghese · 19 minutes ago master
  2. ddbf0f9 Further lower the max bytes threshold used by the Proto Splitter by A. Unique TensorFlower · 34 minutes ago
  3. 8d11b3a [XLA:GPU] Fix host-offloading case for unified estimator. by Greg Olechwierowicz · 44 minutes ago
  4. 1741228 PR #24579: [XLA:CPU][oneDNN] Add SiLU activation for oneDNN contractions by Akhil Goel · 2 hours ago
  5. b0d23b5 [XLA] Clarify memory is HBM related, Fix description of `xla_tpu_rwb_fusion`, remove `xla_tpu_overlap_compute_collective_tc` from the public doc. by A. Unique TensorFlower · 2 hours ago
  6. e82bee7 PR #28402: Bump github/codeql-action from 3.29.0 to 3.29.1 by dependabot[bot] · 3 hours ago
  7. 35cebb9 Add estimation for fragmentation size when computing peak memory usage. by A. Unique TensorFlower · 3 hours ago
  8. 93656cc Add the testcase to validate that collective is used when spmd partitioner handles cross-partition large pad. by A. Unique TensorFlower · 3 hours ago
  9. 6893f58 [xla:cpu] NFC: Move XfeedManager to new location by Eugene Zhulenev · 4 hours ago
  10. a900eeb Automated Code Change by A. Unique TensorFlower · 9 hours ago
  11. 6920d24 Change `HloModule::add_frontend_attributes` to allow adding a single kv pair by Allan Renucci · 10 hours ago
  12. d985287 Remove `--xnnpack_slinky` option by A. Unique TensorFlower · 10 hours ago
  13. 918ec93 Automated Code Change by A. Unique TensorFlower · 12 hours ago
  14. 96f2059 compat: Update forward compatibility horizon to 2025-07-02 by A. Unique TensorFlower · 12 hours ago
  15. 850c1b9 Update GraphDef version to 2276. by A. Unique TensorFlower · 12 hours ago
  16. 497b64e Set half_pixel_centers to negation of align_corners in image resize composite legalization by Chun-nien Chan · 12 hours ago
  17. 276937f [XLA:GPU] Disable horizontal input fusion. by Alexander Belyaev · 12 hours ago
  18. f82d579 [XLA:GPU] Add PipeliningCollectiveAnalyzer. by Greg Olechwierowicz · 12 hours ago
  19. 73510f8 Implement RaggedDot in HloEvaluator by Tori Baker · 13 hours ago
  20. e38be68 [XLA][Numerics][HLO Value Tracking] Add the original value recovery table by Jian Cai · 13 hours ago
  21. 7d57343 Automated Code Change by A. Unique TensorFlower · 15 hours ago
  22. f466e67 [xla] Add an AUTHORS file. by Penporn Koanantakool · 15 hours ago
  23. f7b7ff8 Automated Code Change by A. Unique TensorFlower · 15 hours ago
  24. ef5ac7e Fix a bug where `BufferFromHostLiteral` events are not fulfilled upon allocation failures by Junwhan Ahn · 16 hours ago
  25. 1cf2dc6 [XLA] Refactoring Reduce Window Rewriter to reduce complexity by Ibrahim Umit Akgun · 16 hours ago
  26. 532ec28 Remove redundant logs and cast. by Buddh Prakash · 17 hours ago
  27. e60251b [XLA][SC] Add additional flags to the backend config for the sparsedense grad ops to identify how many values are in the various tuples. by Pankaj Kanwar · 17 hours ago nightly
  28. f590575 [xla] Temporarily skip tests in //xla/tools/hlo_diff on CI due to service outage by Julia Guo · 19 hours ago
  29. 03bbca6 Refactor the code for getting a sharding attribute from mlir::TF::XlaShardingOp. by Bixia Zheng · 19 hours ago
  30. 59f6602 [XLA:CPU] Refactor simple_jit_runner for better benchmarking. by Sean Talts · 22 hours ago
  31. 16889ce is_ci_build: Move from XLA to TSL. by David Pizzuto · 22 hours ago
  32. ff9e517 Ensure there are no isolated TPUDummyInput nodes left behind after simplify_ici_dummy_variables_pass. by A. Unique TensorFlower · 23 hours ago
  33. 77a8499 Enable tests and fix for duplicate registration tests error by Ezekiel Calubaquib · 25 hours ago
  34. 70d137e Move `tensorflow/third_party/triton` to `xla/third_party/triton` by David Dunleavy · 28 hours ago
  35. 0b55b2c [SparseReshapeOp] Microoptimization: Don't call `OpKernelContext::input()` multiple times. by Derek Murray · 28 hours ago
  36. b0b38aa Do not build xnn fusions inside reducers. by A. Unique TensorFlower · 28 hours ago
  37. e797ad7 Add a test case for int4 scatter with unique_indices=true by Adrian Kuegel · 29 hours ago
  38. da48821 Pass AliasInfo to HloAliasAnalysis. by Adrian Kuegel · 30 hours ago
  39. 0b8c274 [XLA:GPU] Deprecate CUBLAS_GEMM_DEFAULT_TENSOR_OP. by Dirk Hornung · 31 hours ago
  40. 1db711b Merge pull request #86172 from Intel-tensorflow:gaurides/mm_fusion by TensorFlower Gardener · 32 hours ago
  41. 193ff96 [XLA:GPU] check if producer / consumer can be fused in CanFuseTriton by Mikhail Goncharov · 35 hours ago
  42. 33373af [XLA:CPU] Set loaded workgroup as invariant & fix incorrect alignment metadata. by Will Froom · 36 hours ago
  43. 30077d8 [XLA:GPU] Fix the implementation of the TMA viability filter to conform to the Nvidia documentation by Mohammed Anany · 36 hours ago
  44. a26370d compat: Update forward compatibility horizon to 2025-07-01 by A. Unique TensorFlower · 36 hours ago
  45. 5ce11a5 Update GraphDef version to 2275. by A. Unique TensorFlower · 2 days ago
  46. f3dd88c Add use_shardy_partitioner in `TPUCompileMetadataProto` and `TpuAotCompilationOptions`. The default value is false. by Zixuan Jiang · 2 days ago
  47. f1697d6 [XLA] Add after target rule kDelay rule and use it in aggressive flexible scheduling by Marcello Maggioni · 2 days ago
  48. cc92a56 unicode_ops: Encode noncharacters by Jesse Rosenstock · 2 days ago
  49. 089746a Merge pull request #95322 from linux-on-ibm-z:tf-2.19.0-s390x-fix by TensorFlower Gardener · 2 days ago
  50. 102c3c3 Automated Code Change by A. Unique TensorFlower · 2 days ago
  51. 0989289 Automated Code Change by A. Unique TensorFlower · 2 days ago
  52. 395b1d6 PR #28394: [XLA:GPU] Add DynamicSliceCopyFusion command to command buffer. by Shaogang Wang · 2 days ago
  53. 01bfa9f Add CreateRawAliasOfBuffer() to CommonPjRtBufferImpl. by Parker Schuh · 2 days ago
  54. 3d5d0e4 Simplify ComputationPlacer interface. by Toli Yevtushenko · 2 days ago
  55. b166865 Add initial support for reductions in XnnGraphFusion. by A. Unique TensorFlower · 2 days ago
  56. fad6b3c Fix invalid process count bug? by Michael Whittaker · 2 days ago
  57. 43eac95 Fix: Shardy should propagate use_auto_spmd_partitioning field from config by A. Unique TensorFlower · 2 days ago
  58. 34ad9a2 Update version of rules_ml_toolchain repo. by A. Unique TensorFlower · 2 days ago
  59. c0b1508 1. Limit the max-width and max-height of a cell. by A. Unique TensorFlower · 2 days ago
  60. cc445fe Integrate StableHLO at openxla/stablehlo@9df3b556 by Abhinav Gunjal · 2 days ago
  61. fd417fa Refactor `py_import` macros to avoid unpacking pypi wheels twice. by A. Unique TensorFlower · 2 days ago
  62. 58bae0d Announcement about deprecating tf lite within TF. by Francisco Unda · 2 days ago
  63. 869d80b fix clang format by Gauri Deshpande · 2 days ago
  64. e2ee8cf add no_oss_py313 tag to following max python test by Ezekiel Calubaquib · 2 days ago
  65. 90d3a17 Check operands of elementwise ops offloaded to xnnpack. by A. Unique TensorFlower · 2 days ago
  66. 5c398c8 Added a XLA Flags Guidance doc by A. Unique TensorFlower · 2 days ago
  67. 157684d Remove device shape & device size bytes functions from HLO runners. by Niklas Vangerow · 2 days ago
  68. 8d3a9e3 [xla:pjrt] Add PjRtFuture::TryMap to map futures when map functor itself can fail by Eugene Zhulenev · 2 days ago
  69. 1d00a61 [xla:cpu] Decouple xfeed manager from legacy cpu_runtime by Eugene Zhulenev · 2 days ago
  70. dcbc119 Rollback due to suspected correctness issues. by Michael Kuperstein · 2 days ago
  71. 9fc3f19 [XLA] Add a length limit on op_name when concatenating in call_inliner. by Peter Hawkins · 2 days ago
  72. 8455117 Merge pull request #96174 from tensorflow:Venkat6871-patch-1 by TensorFlower Gardener · 2 days ago
  73. 8ef8ad3 Correctly remove user from assignees list by Mihai Maruseac · 2 days ago
  74. 9885dec Don't handle empty reductions in XNNPACK delegate by A. Unique TensorFlower · 2 days ago
  75. 038ae36 [XLA:GPU] Record reification cost only for supported instructions. by Greg Olechwierowicz · 2 days ago
  76. 3df1f29 [XLA:CPU] Add dereferenceable metadata to loaded argument pointer. by Will Froom · 2 days ago
  77. e3d72aa [XLA:GPU] Code cleanups: by Allan Renucci · 2 days ago
  78. 64146f1 Fix a problem in Shape::Equal in comparing buffer types. by Bixia Zheng · 2 days ago
  79. 98e17eb [XLA:GPU] Make gpu_hlo_schedule testing cover unified latency estimator cases. by Greg Olechwierowicz · 2 days ago
  80. 6bc2f9a [XLA:CPU][XLA:GPU] Use llvm array types for GEP when lowering tensors. by Will Froom · 2 days ago
  81. b4d9e4c Added support for the following to allow PtrVec to replace by A. Unique TensorFlower · 2 days ago
  82. 978a2a4 [XLA:GPU] add lock guards for containers in priority_fusion by Mikhail Goncharov · 2 days ago
  83. 0ec53a6 Make XNNPack weight cache work with files bigger than 2 GiB on Windows. by Quentin Khan · 2 days ago
  84. 475329d PR #26217: [XLA:GPU] Add Intel GPU specific tags for xla and sysl_status component by Kanvi Khanna · 2 days ago
  85. 08987fd Update GraphDef version to 2274. by A. Unique TensorFlower · 2 days ago
  86. f88de2a Automated Code Change by A. Unique TensorFlower · 2 days ago
  87. e14e765 compat: Update forward compatibility horizon to 2025-06-30 by A. Unique TensorFlower · 2 days ago
  88. add56ec [XLA:GPU] Enforce compile-time exhaustiveness of `GemmFusionAutotuner::BackendConfig` visitors. by Benjamin Chetioui · 2 days ago
  89. 2b56939 Automated Code Change by A. Unique TensorFlower · 2 days ago
  90. 8476d2d Automated Code Change by A. Unique TensorFlower · 3 days ago
  91. a79b5e6 Automated Code Change by A. Unique TensorFlower · 3 days ago
  92. 49a73f2 [HLO Graph Dumper] Add the computation name to the op name when annotating parameters. by Thomas Joerg · 3 days ago
  93. 2fccd12 PR #25298: [XLA:GPU] cudnn sdpa flex attention by Shanbin Ke · 3 days ago
  94. 7f51cf0 Update bot_config.yml by Venkat6871 · 3 days ago
  95. 303d1f9 [XLA:GPU] Lifting int4_pass above TritonXlaExtractInsertPass. This is necessary to allow both the legacy Triton emitter and the Generic emitter to correctly handle int4. This also includes accommodating new instructions in the pass. by Mohammed Anany · 3 days ago
  96. f147951 Update GraphDef version to 2273. by A. Unique TensorFlower · 3 days ago
  97. c396b63 compat: Update forward compatibility horizon to 2025-06-29 by A. Unique TensorFlower · 4 days ago
  98. d5e7eb3 Automated Code Change by A. Unique TensorFlower · 4 days ago
  99. 9fc04b6 Do not propagate name_stacks into lower_jaxpr_to_fun. by Peter Hawkins · 4 days ago
  100. 6a8f104 Populate the HLO op_type field from JAX StableHLO. by Peter Hawkins · 4 days ago