Google Git Google Git
Sign in
opensecura/3p/openxla/iree/HEAD
  1. c6882b8 Integrate LLVM to llvm/llvm-project@bdd8381f5b7e (#25103) by Stefan Schuermans · 3 days ago main
  2. 9ea0d95 [Runtime][VM] connect ISA decoder validation macros and tighten register verification (#25088) by m00dy · 3 days ago
  3. f1eb9ce [Bazel] Fix flatcc and bitcode library include paths when IREE is an external repo (#25101) by Stefan Schuermans · 4 days ago latest-snapshot
  4. e7490c3 [Codegen][CPU] Lower RISC-V V f16 vfmacc, vfwmacc, and Zvfhmin inner_tiled MMA. (#25000) by tm · 4 days ago
  5. 9ea0f2f [LLVMCPU] Align scalable distribution tiles to base * vscaleMax (#24849) by Ege Beysel · 5 days ago
  6. 624f6da [WebGPU] Retain resources referenced by command buffers (#25070) by Anutosh Bhat · 5 days ago
  7. 4a289db [WebGPU] Preserve Wasm host pointer widths (#25075) by Anutosh Bhat · 5 days ago
  8. 4a9d601 Integrate LLVM to llvm/llvm-project@03ddfac14e84 (#25082) by Stefan Schuermans · 6 days ago
  9. 615ed84 Version bump to 3.14 (#25080) by Tobias Fuchs · 6 days ago
  10. 726f91a [Util] Fix crash in MergeIndexSwitchPattern when second op yields outer values (#25038) by jonathansong · 6 days ago
  11. 0d0d2d2 [Util] Ensure scf.index_switch ops share the same selector before merging (#25037) by jonathansong · 6 days ago
  12. 10f7361 [SPIRV] Unroll wide elementwise vector operations (#25053) by Anutosh Bhat · 6 days ago
  13. 845a59a [Runtime][Bindings] Fix several memory leaks in python bindings (#25014) by Florian Walbroel · 6 days ago
  14. e76d73d [WebGPU] Retain builtin buffers until submission (#25068) by Anutosh Bhat · 6 days ago
  15. e4387cb [GlobalOptimization] Make im2col a generic convolution rewrite (#25011) by ziereis · 6 days ago
  16. 2fa8219 [Runtime][WASM] Handle wasm64 pointers in JS completion drains (#25054) by Anutosh Bhat · 7 days ago
  17. 58c31ac Integrate LLVM to llvm/llvm-project@6be022066fd2 (#25045) by Stefan Schuermans · 7 days ago
  18. 94be865 [docs] Add tuner to release management docs (#22646) by RattataKing · 7 days ago
  19. 4bab48f [DispatchCreation] Preserve the target of materialized tensor layouts (#24968) by maxbartel · 7 days ago
  20. 2db1911 [SPIRV] Fix WebGPU SPIR-V client API detection (#25051) by Anutosh Bhat · 7 days ago
  21. 680ff4d [CMake] Honor IREE_HOST_BIN_DIR for compiler TableGen (#25049) by Anutosh Bhat · 7 days ago
  22. 89ece87 [Torch] Convert PT2E per-token quantization to LinalgExt (#25024) by Roberto Laudani · 10 days ago
  23. 697057d [Integrate] Update torch-mlir to 201b80fb (#25046) by Roberto Laudani · 10 days ago
  24. b8872c6 [Codegen] Add bufferization support for CastToRaggedShapeOp and LinearizeRaggedDimsOp (#24193) by MaheshRavishankar · 11 days ago
  25. 8fe6062 [Torch] Preserve PT2E per-channel-group quantization as LinalgExt ops (#25008) by Roberto Laudani · 11 days ago
  26. d5cf4e0 Fix async backend selection for Emscripten and wasm64 (#25042) by Anutosh Bhat · 11 days ago
  27. 16d3934 [Vulkan] Accept foreign semaphores in queue operations (#25010) by Tobias Fuchs · 11 days ago
  28. eb7846f [Codegen] Forward temporary DPS output copies (#24727) by smart-moomoo · 12 days ago
  29. ccad585 Bump the github-actions group with 2 updates (#25039) by dependabot[bot] · 12 days ago
  30. 2dbb707 [Codegen][GPU] Add RDNA4 materialize encoding test (#24924) by Prajit Rahul · 12 days ago
  31. 17fb04d [HAL] Add command buffer flush and invalidate operations (#24945) by purnima shrivastava · 12 days ago
  32. 6daf6ea [DispatchCreation] Fuse packed contractions with epilogues and unpack (#24967) by maxbartel · 12 days ago
  33. 3480ce7 [Vulkan] Keep a rejected queue_dealloca from clearing pending flag (#25003) by Tobias Fuchs · 12 days ago
  34. 0be4149 Update release process (#25002) by Tobias Fuchs · 12 days ago
  35. 7a8b003 [CI] Disable job test_onnx_models::amdgpu_vulkan_rdna3 (#25033) by Jelle Schühmacher · 12 days ago
  36. 04028a8 [GlobalOptimization] Fold empty-set reductions to their init operand. (#24949) by Yalong · 12 days ago
  37. cb9c3c8 [Stream] Always map aliases to resolved resource ranges of the source op (#25026) by Artem Gindinson · 13 days ago
  38. d699c04 [Samples] Add an out-of-tree compiler plugin (#24896) by Jelle Schühmacher · 13 days ago
  39. 99781d9 Integrate LLVM to llvm/llvm-project@32d702efa29d (#25025) by Stefan Schuermans · 13 days ago
  40. 388e65c [GlobalOptimization] Propagate affine QDQ through tensor operations (#24906) by ziereis · 13 days ago
  41. 3fd498c [HAL] Reject buffer view size overflows (#24992) by Goutam Adwant · 2 weeks ago
  42. fe99fa5 [Runtime][Bindings] support async parameter file loading (#24988) by Christopher McGirr · 2 weeks ago
  43. 08f0f57 [iree-benchmark-module] Add dispatch timing rows (#24987) by maxbartel · 2 weeks ago
  44. de54be6 [LLVMGPU] Re-land FP8 mma.sync transpose shape fix (#25015) by WMC · 2 weeks ago
  45. ed65de2 Integrate LLVM to llvm/llvm-project@7e751154a0e5 (#25009) by Pooja Hemashekar · 2 weeks ago
  46. 8f79b94 Revert "[LLVMGPU] Fix hardcoded LHS transpose shape in NV mma.sync lowering" (#25012) by Artem Gindinson · 2 weeks ago
  47. e97b240 [LLVMGPU] Fix hardcoded LHS transpose shape in NV mma.sync lowering (#24676) by WMC · 3 weeks ago
  48. 6ddc991 [LinalgExt] Add a output sizes < number of batch dims check in `iree_linalg_ext.im2col` verifier (#24925) by Ayokunle Amodu · 3 weeks ago
  49. 27e20aa [CI] Migrate macOS 14 to macOS 15 (#25006) by Jelle Schühmacher · 3 weeks ago
  50. 705c948 Update to IREE website community sections (#24995) by Rod Burns · 3 weeks ago
  51. 709595d [CI] Run Vulkan HAL CTS under rocjitsu (#25001) by Jakub Kuderski · 3 weeks ago
  52. 4fcf192 Fix build after properties migration (#25004) by Jelle Schühmacher · 3 weeks ago
  53. 1d34a28 Migrate IREE dialects to strict properties (#24983) by Jelle Schühmacher · 3 weeks ago
  54. 4fc29b6 [Torch] Preserve PT2E quantization as LinalgExt ops (#24918) by ziereis · 3 weeks ago
  55. 5d42a67 [CI] Add RDNA3 and RDNA4 Vulkan SPIR-V e2e tests under rocjitsu (#24990) by Jakub Kuderski · 3 weeks ago
  56. 466f8d3 [DispatchCreation] Propagate tensor encodings outside dispatch regions (#24966) by maxbartel · 3 weeks ago
  57. 2601b70 [Bindings][Compiler] Add Bazel support for Python bindings (#24980) by Christopher McGirr · 3 weeks ago
  58. f2aff78 [GlobalOpt] Keep strided input maps when the producer can fuse (#24950) by Pan Zhang · 3 weeks ago
  59. 8823fe6 [Integrate] Update torch-mlir to 528d3dcb (#24908) by ziereis · 3 weeks ago
  60. 887e0b6 Bump dawidd6/action-download-artifact from 25 to 27 in the github-actions group (#24998) by dependabot[bot] · 3 weeks ago
  61. b315d00 [iree-benchmark-module] Unify sync, async and dispatch execution (#24986) by maxbartel · 3 weeks ago
  62. 480cbbb [Runtime][Python] Keep all results in benchmark_module (#24985) by maxbartel · 3 weeks ago
  63. 7fd5f9a [DispatchCreation] Normalize contraction dimensions outside dispatches (#24965) by maxbartel · 3 weeks ago
  64. ec6edc5 [Bazel] use execution paths for genrule inputs (#24981) by Christopher McGirr · 3 weeks ago
  65. 6610b23 [PluginAPI] Support in-tree dynamic compiler plugins (#24894) by Jelle Schühmacher · 3 weeks ago
  66. 84757b5 Version bump to 3.13 after 3.12 release (#24994) by Tobias Fuchs · 3 weeks ago
  67. 8e6546f [NFC] Use checks from upstream MLIR (#24984) by Alex Denisov · 3 weeks ago
  68. 0373956 [CI] Add job with dynamic plugins enabled (#24893) by Jelle Schühmacher · 3 weeks ago
  69. c946164 Integrate LLVM to llvm/llvm-project@a938559a9145 (#24982) by Jelle Schühmacher · 3 weeks ago
  70. a3ec918 [Codegen][CPU] Add RISC-V V f32 vfmacc.vf inner_tiled MMA. (#24933) by tm · 3 weeks ago
  71. 834b0b6 [LLVMGPU] Add RDNA3 e2e attention correctness tests (#24948) by WMC · 3 weeks ago
  72. 5503db0 fix(PackConstants): don't start new storage buffer if current one is still empty (#23927) by Stefan Schuermans · 3 weeks ago
  73. ffd36aa [VM] Preserve 64-bit values in internal calls (#24946) by Pan Zhang · 3 weeks ago
  74. 76caa89 [GlobalOptimization] Expose reusable transpose propagation patterns (#24978) by ziereis · 3 weeks ago
  75. 9b64325 [Bazel] Resolve IREE paths and labels in external consumers (#24977) by Christopher McGirr · 4 weeks ago
  76. e7e1fb4 [CUDA] Raise the default PTX level for sm_89, sm_120 and sm_121 (#24976) by Samarth Narang · 4 weeks ago
  77. 315c3a3 [CI] Optimize stacked PR behavior (#24979) by Jelle Schühmacher · 4 weeks ago
  78. a01adac [Flow] Prevent empty tensor refinement from breaking Stream lowering (#24957) by Jelle Schühmacher · 4 weeks ago
  79. e4becc9 Bump the github-actions group with 2 updates (#24971) by dependabot[bot] · 4 weeks ago
  80. f3bea69 [PluginAPI] Experimental support for dynamic compiler plugins (#24892) by Jelle Schühmacher · 4 weeks ago
  81. 199565e Integrate LLVM to llvm/llvm-project@a98f7ed68e (#24963) by Artem Gindinson · 4 weeks ago
  82. 24470e9 [Stream] Fix O(N²) compile-time scaling in partitionRegionConcurrency (#24958) by Isabelle Lai · 4 weeks ago
  83. 374ab39 [spirv] Do not propagate workgroup tiling to fused ops (#24961) by Alex Denisov · 4 weeks ago
  84. 5cf0a12 [Build] Stop CMake riscv64 defaults from clobbering test cpu-features (#24866) by TMahlatini · 4 weeks ago
  85. c83444b [StableHLO] Lower the bounds encoding to util.assume.int (#24939) by Jelle Schühmacher · 4 weeks ago
  86. bfdd577 [WASM] Add missing f64 musl builtins for ONNX operations (#24953) by Prajit Rahul · 4 weeks ago
  87. 8bbd58b [LLVMGPU] Add a check for the number of workgroup tile sizes in a config (#24916) by Ayokunle Amodu · 4 weeks ago
  88. 3f1d7ae [LinalgExt] Canonicalize zero zero-points in affine QDQ ops (#24905) by ziereis · 5 weeks ago
  89. 4c5f6cb [GlobalOptimization] Rewrite QDQ contractions into integer math (#24902) by ziereis · 5 weeks ago
  90. bd828d2 Bump cpp-linter/cpp-linter-action from 2.21.0 to 2.22.0 in the github-actions group (#24954) by dependabot[bot] · 5 weeks ago
  91. f7f1068 [CI] Adjust for decommissioned runners (#24951) by Jelle Schühmacher · 5 weeks ago
  92. 6ef606b Integrate LLVM to llvm/llvm-project@b2b38d4b3352 (#24944) by Jelle Schühmacher · 5 weeks ago
  93. 37c131a [StableHLO] Fold constant-operand dynamic ops to static forms (#24938) by Jelle Schühmacher · 5 weeks ago
  94. b929b14 [Flow] Add a folder for `flow.tensor.encode` to the same layout (#24921) by Ayokunle Amodu · 5 weeks ago
  95. a5ca3e2 [VMVX] Added math.fma to vm.fma lowering (#24915) by Ayokunle Amodu · 5 weeks ago
  96. 233bd5d Integrate LLVM to llvm/llvm-project@c53000a7282b (#24935) by Jelle Schühmacher · 5 weeks ago
  97. 785dacd [LLVMCPU] Add vscale_range target field, require it for scalable vec (#24848) by Ege Beysel · 5 weeks ago
  98. 2b05c5d [CUDA] Preserve executable export names independently from PTX symbols (#24889) by WMC · 6 weeks ago
  99. 389229e [Compiler] Rename the compiler's LLVM/MLIR symbols (#24891) by Jelle Schühmacher · 6 weeks ago
  100. 83265e8 [CI] Drop package tests tied to Threadripper and W7900x2 (#24934) by Jakub Kuderski · 6 weeks ago