Google Git
Sign in
opensecura/3p/openxla/iree/HEAD
  1. 9983d03 [local-task] Clamp file read/write lengths to the platform transfer limit (#24816) by ziereis · 2 days ago main
  2. b1b5ffa [iree-benchmark-module] transfer outputs to host in case of enable_output_processing (#24821) by Stefan Schuermans · 2 days ago
  3. 1e43d54 Fix Python HAL device creation params only last one used (#24812) by Shogo Yamazaki · 2 days ago
  4. 8d489e2 [Docs][GitHub] Improve the automated PR greeting message (#24819) by Artem Gindinson · 2 days ago latest-snapshot
  5. a82330a [DispatchCreation] Allow hoisting of set_encoding through generics with a transposed output map (#24800) by Alex Denisov · 3 days ago
  6. 3c2a79f [DispatchCreation] Fix GatherFusionPattern on a scalar producer operand (#24803) by ziereis · 5 days ago
  7. 95a0035 [Codegen] Support multi-output consumers with permuted indexing maps (#24768) by Artem Gindinson · 6 days ago
  8. cf9453f [LLVMCPU] add inner-tile-alignment hint attribute (#24806) by Ege Beysel · 6 days ago
  9. b9a8b77 [Codegen][LLVMCPU] Split loadProcessorData: hoist only the alloca (#24786) by Ege Beysel · 6 days ago
  10. bff05a9 Instate initial technical steering committee (#24790) by Jelle Schühmacher · 7 days ago
  11. 5e00875 [LIT] Migrate tests lit config to the internal shell (#24810) by Zohaib · 7 days ago
  12. 4734258 [Util] Filter non-returning region terminators (#24795) by Pan Zhang · 7 days ago
  13. c9058ce Integrate LLVM to llvm/llvm-project@6ea395e4fe4d (#24805) by Roberto Laudani · 7 days ago
  14. 5973724 Fix arena allocation alignment at the block boundary (#24773) by Kushida · 8 days ago
  15. 8b6328a [LLVMCPU] Use native bf16 converts when the target supports them (#24759) by Zmicier Prybysh · 8 days ago
  16. c1ecdbb Fix iree_status_format capacity checks for partial buffer fills (#24797) by Irfan Hussain · 8 days ago
  17. bb8e098 [Runtime][Python] Fix multiple f64 return values (#24796) by Pan Zhang · 9 days ago
  18. 60903f1 [LIT] Migrate runtime lit config to the internal shell (#24794) by Zohaib · 10 days ago
  19. 3699452 [LLVMGPU] Add NVVM paged attention pipeline test (#24770) by WMC · 12 days ago
  20. a70389b [iree-benchmark-module] support processing outputs after benchmarking (#24789) by Stefan Schuermans · 12 days ago
  21. 610a82f [PreProcessing] Support quantized convolutions in channels-last conversion (#24780) by Murari G · 12 days ago
  22. c6c633d Integrate LLVM to llvm/llvm-project@480b2c9eb47f (#24793) by Ege Beysel · 12 days ago
  23. 2dd1514 [CI] Sunset MacOS x64 runners (#24792) by Jelle Schühmacher · 12 days ago
  24. 7dd0031 add stablehlo pass to convert IR with quantized types to standard types (#24785) by ziereis · 13 days ago
  25. 4ecdc3d [LLVM integrate] drop carried LLVM commit reverts (#24779) by Stefan Schuermans · 14 days ago
  26. 175f034 Fix out-of-bounds crash in Stream affinity analysis for scf.while (#24723) by pstarkcdpr · 14 days ago
  27. 13d9ad9 [Codegen] Lower data-tiled conv to conv_nchwc ukernel (#24730) by Pooja Hemashekar · 2 weeks ago
  28. 83076f9 [CI] Decommission mi308/mi325 runners (#24782) by Jelle Schühmacher · 2 weeks ago
  29. 18c3da6 [StableHLO] Legalize composite ops to calls in the input pipeline (#24777) by pstarkcdpr · 3 weeks ago
  30. 21c6cd2 [Preprocessing] Handle batching dims and dynamic-update-slice scatter ops (#24720) by pstarkcdpr · 3 weeks ago
  31. 100a1d3 [Build] set CCACHE_SLOPPINESS to enable ccache with PCH (#24757) by Jelle Schühmacher · 3 weeks ago
  32. 4aa302d [LinalgExt] Implement CustomOp::getStaticLoopRanges (#24734) by Pan Zhang · 3 weeks ago
  33. 47a54e6 [RVV] Enable SpaceMiT vendor IME (#24706) by TMahlatini · 3 weeks ago
  34. e7a3005 [Flow] Fix TensorSliceOp::fold for parameter attributes (#24762) by Pan Zhang · 3 weeks ago
  35. 442c605 [LLVMGPU] Add NVIDIA FP8 mma.sync intrinsics for sm_89 and sm_120 (#24659) by WMC · 3 weeks ago
  36. df5f718 [Stream] Model execution affinity for cross-device transfers (#24748) by ziereis · 3 weeks ago
  37. 01d3cd5 Bump the github-actions group with 4 updates (#24731) by dependabot[bot] · 3 weeks ago
  38. 3eb9bba [Stream] Fold transferred stream clones into minimal slices before loads (#24740) by Lekkala_Sravya-mcw · 3 weeks ago
  39. 5fb1679 Optional sync func conversion (#24747) by Jelle Schühmacher · 3 weeks ago
  40. 4fa94fa [Runtime][RISCV] Detect `Zvfbfwma` via hwprobe for the bf16 mmt4d ukernel (#24767) by Zmicier Prybysh · 3 weeks ago
  41. a245917 [Build] Fix GCC build (#24756) by Jelle Schühmacher · 3 weeks ago
  42. 0c639cd Integrate LLVM to llvm/llvm-project@e7fac4e39085 (#24765) by Tobias Fuchs · 3 weeks ago
  43. c3ad7f4 [Docs] RVV Pipeline Blogpost (#24758) by Ege Beysel · 3 weeks ago
  44. a0465a3 [Runtime] Add initial data-tiled conv ukernel (generic & avx512) (#24729) by Pooja Hemashekar · 3 weeks ago
  45. 16396e4 [LLVMCPU] Fix scalable vectorization fallback on SME-only (no `+sve`) targets (#24693) by Federico Bruzzone · 4 weeks ago
  46. 35b2070 [Codegen][LLVMCPU] Hoist in-loop stack alloca (#24749) by Federico Bruzzone · 4 weeks ago
  47. 5e31a84 [Codegen] KernelDispatch recognition and tiling for data-tiled conv (#24716) by Pooja Hemashekar · 4 weeks ago
  48. b60b87c Integrate LLVM to llvm/llvm-project@a3ae4996bb22 (#24750) by Maksymilian B. Knust · 4 weeks ago
  49. 0071307 Fix samples build (#24743) by Jelle Schühmacher · 4 weeks ago
  50. ac3e5af [Codegen] Materialize encoding info for convolution with NCHWc layout (#24714) by Pooja Hemashekar · 4 weeks ago
  51. e494511 [LinalgExt][Attention] Specialize generics to matmuls (#24668) by Kamil Karwacki · 4 weeks ago
  52. bc908fd [LLVMCPU][RISCV] Add RVV bf16 mmt4d ukernel using the Zvfbfwma widening MAC (bf16*bf16->f32) (#24695) by Zmicier Prybysh · 4 weeks ago
  53. e53a335 [LIT][LLVMCPU] fix failing rvv lowering strategy test (#24739) by Ege Beysel · 4 weeks ago
  54. f9f4c9d [Codegen][LLVMCPU] fix tile size selection for consumer unpack ops (#24709) by Ege Beysel · 4 weeks ago
  55. adb2986 [DT][CPU]: scalable tile size selection for RVV (#24601) by Ege Beysel · 4 weeks ago
  56. d02dcc6 [CMake] Propagate WILL_FAIL through test rules (#24707) by Pan Zhang · 4 weeks ago
  57. d56cb80 Integrate LLVM to llvm/llvm-project@ae7f0db2a0d6 (#24733) by Maksymilian B. Knust · 4 weeks ago
  58. dc9601f [LinalgExt] Fix WinogradInputTransformOp::verify incorrect dim-1 dynamic check (#24679) by Eylon Eliyahu Krause · 4 weeks ago
  59. f2bcea1 [Util] Fix 32-bit wrap of util.string.format placeholder-count check (#24685) by Eylon Eliyahu Krause · 4 weeks ago
  60. e8ad3fa Drop CodegenPipelineOptLevel and use llvm::OptimizationLevel (#24728) by huang-me · 4 weeks ago
  61. b94a5a5 [DT][CPU]: RVV scalable encoding materialization (#24600) by Ege Beysel · 4 weeks ago
  62. 4cf1a7c [CPU] Vectorize parallel dims for non-AVX512 x86 matmul defaults (#24701) by pstarkcdpr · 4 weeks ago
  63. a869dc3 Integrate LLVM to llvm/llvm-project@4641f4879e47 (#24713) by juanigp · 5 weeks ago
  64. 9c7d2ae [DispatchCreation] Register enum literals for parsing data-tiling hint op types (#24711) by Pooja Hemashekar · 5 weeks ago
  65. 4b11e1d [LLVMCPU] Add SME lowering-strategy tests for f64 and unsupported i8 matmuls (#24656) by Federico Bruzzone · 5 weeks ago
  66. dd35052 [Stream] Deduplicate identical tensor import/export ops (#24655) by Lekkala_Sravya-mcw · 5 weeks ago
  67. 810db8e [Stream] Bounds-check tied operand index in verifyTiedOperandEncodings (#24686) by Eylon Eliyahu Krause · 5 weeks ago
  68. a73ba39 Integrate LLVM to llvm/llvm-project@abbcebe65284 (#24704) by juanigp · 5 weeks ago
  69. 5051d70 [CI] Split the welcome message workflow for issue/PR (#24705) by Artem Gindinson · 5 weeks ago
  70. 0893eac Fix compile error when hoisting constants. (#24672) by pstarkcdpr · 5 weeks ago
  71. ff836d7 [Docs][Github] Add initial automated first-time contributor message (#24702) by Artem Gindinson · 5 weeks ago
  72. 42ff6d7 [CI] Decomission amd gpu runners (#24703) by maxbartel · 5 weeks ago
  73. d495a53 [Torch] Support explicit scale values from `tm_tensor.attention` (#24566) by Artem Gindinson · 6 weeks ago
  74. 934cccb Integrate LLVM to llvm/llvm-project@c138fc9acfdd (#24699) by Maksymilian B. Knust · 6 weeks ago
  75. 774d7bf [GlobalOpt] Add pass to convert broadcast batch_matmul to matmul (#24670) by Roberto Laudani · 6 weeks ago
  76. 6caa917 Integrate Torch-MLIR to llvm/torch-mlir@1828c5053 (#24691) by Artem Gindinson · 6 weeks ago
  77. 39088ea [ROCDL] Set relaxed buffer OOB mode (#24692) by Krzysztof Drewniak · 6 weeks ago
  78. 4b23615 [Stream] Fix crash in ConvertSplatConstantsIntoSplats for dense_resource (#24683) by z combinator · 6 weeks ago
  79. 8234462 Integrate LLVM to llvm/llvm-project@fcd02ae7caf2 (#24690) by Maksymilian B. Knust · 6 weeks ago
  80. 481c3c1 [LLVMCPU] Fix ArmSME requiring classic SVE, breaking SME-only targets (e.g., Apple Silicon) (#24661) by Federico Bruzzone · 6 weeks ago
  81. 9080be2 [Flow][NFC] Optimize dispatch annotation type string generation (#24675) by Akun · 6 weeks ago
  82. a33484e [Runtime] Honor the base argument in atoi_int32_base (#24677) by Eylon Eliyahu Krause · 6 weeks ago
  83. 78aff2f [InputConversion][TOSA]: change TOSA level to none (#24667) by Christopher McGirr · 6 weeks ago
  84. 38afe0a Address crash in iree-reduce with complex tensors (#24674) by pstarkcdpr · 6 weeks ago
  85. 21a6748 Integrate LLVM to llvm/llvm-project@bb315b7e2953 (#24666) by Tobias Fuchs · 7 weeks ago
  86. 2ce6926 [Codegen][CPU] Fill in the bf16 and i8 ukernel bodies + e2e tests. (#24572) by Benoit Jacob · 7 weeks ago
  87. aab676a [NFC] Remove @bjacob from CODEOWNERS. (#24669) by Benoit Jacob · 7 weeks ago
  88. 07d4cd5 [Flow] Fold chained tensor.slice ops (#24628) by Lekkala_Sravya-mcw · 7 weeks ago
  89. 1e4c8a8 [ROCM] Validate that target triple is set in module and test for it (#24663) by Stefan Schuermans · 7 weeks ago
  90. 68206a1 Integrate LLVM to llvm/llvm-project@9c51ed38f1e2 (#24662) by Stefan Schuermans · 7 weeks ago
  91. 4d4e97d [StableHLO] Guard convolution widen operand fusion (#24424) by Yuwei Sun · 7 weeks ago
  92. af08a7c [DispatchCreation] Hoist scalar tensor.extract and tensor.extract_slice (#24552) by juanigp · 7 weeks ago
  93. be57650 [Codegen][CPU] Drop the ACC stride from the inner_tiled ukernel ABI. (#24652) by Benoit Jacob · 7 weeks ago
  94. 6ec0a37 [Website] Update copyright year in the global footer (#24657) by Artem Gindinson · 7 weeks ago
  95. 50d0add [Docs][Website] Add instructions of how to integrate newer LLVM (#24631) by Stefan Schuermans · 7 weeks ago
  96. 1781228 [Codegen][DispatchCreation] Separate dispatch for iree_linalg_ext.scan producers (#24651) by Christopher McGirr · 7 weeks ago
  97. a4d0287 [CUDA][LLVMGPU] Fix sm_120 WGP params and add BF16 mma.sync coverage (#24648) by WMC · 7 weeks ago
  98. 540008c [Metal] Fix indirect dispatch offset for sub-allocated parameter buffers (#24644) by Alex Vasile · 7 weeks ago
  99. 42f300c [Metal] Fix staging buffer overflow on large update_buffer uploads (#24643) by Alex Vasile · 7 weeks ago
  100. fa27b1c [Metal] Carry export name separately from MSL entry point for name lookup (#24642) by Alex Vasile · 7 weeks ago