Skip to content

Issues: iree-org/iree

Release tracker - 2024/09
#18432 opened Sep 4, 2024 by ScottTodd
Open
Pending LLVM Dependent Patches
#15685 opened Nov 27, 2023 by stellaraccident
Open 4
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

979 Open 2,910 Closed
979 Open 2,910 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Add Apple GPU runners and run Metal tests again hal/metal Runtime Apple Metal HAL backend infrastructure Relating to build systems, CI, or testing platform/macos 🍎 MacOS-specific build, execution, benchmarking, and deployment
#18817 opened Oct 17, 2024 by ScottTodd
Add NVIDIA GPU runners and run CUDA tests again codegen/nvvm NVVM code generation compiler backend codegen/spirv SPIR-V code generation compiler backend hal/cuda Runtime CUDA HAL backend hal/vulkan Runtime Vulkan GPU HAL backend infrastructure Relating to build systems, CI, or testing
#18814 opened Oct 17, 2024 by ScottTodd
@Eliasj42
Run Windows build/test workflows more regularly infrastructure Relating to build systems, CI, or testing platform/windows 🚪 Windows-specific build, execution, benchmarking, and deployment
#18813 opened Oct 17, 2024 by ScottTodd
@Eliasj42
1
Does IREE support native cuda buffer VM invocation or is there any chance to improve the performance of result torch tensors construction?
#18811 opened Oct 17, 2024 by LWenH
2
Does IREE currently support large language models? support Request support or ask a question
#18807 opened Oct 17, 2024 by pyl3000
@rsuderman
Rework iree-compile pipeline for ONNX enhancement ➕ New feature or request
#18803 opened Oct 17, 2024 by zjgarvey
@zjgarvey @vivekkhandelwal1
4
In-place argument updates with device affinities fails bug 🐞 Something isn't working
#18802 opened Oct 16, 2024 by sogartar
[Codegen][AMDGPU Backend] Correctness issue for conv_2d_ngchw_gfchw bug 🐞 Something isn't working codegen/llvm LLVM code generation compiler backend codegen/rocm ROCm code generation compiler backend (HIP/HSA)
#18798 opened Oct 16, 2024 by qedawkins
2
Rename iree-hip- compiler flags to iree-rocm- when they apply to codegen. cleanup 🧹 codegen/rocm ROCm code generation compiler backend (HIP/HSA)
#18792 opened Oct 16, 2024 by benvanik
3
[GPU] : HSA_STATUS_ERROR_MEMORY_APERTURE_VIOLATION in GPU while passing inference in CPU bug 🐞 Something isn't working
#18789 opened Oct 16, 2024 by pdhirajkumarprasad
6
HoistIntoGlobals fails to hoist constantOp bug 🐞 Something isn't working compiler/dialects Relating to the IREE compiler dialects (flow, hal, vm)
#18779 opened Oct 15, 2024 by ziereis
2
Bufferization needs tensor.extract_slice to bufferize in place
#18778 opened Oct 15, 2024 by Max191
@Max191
1
When importing onnx model, do I convert onnx to torch dialect? integrations/onnx ONNX integration work support Request support or ask a question
#18775 opened Oct 15, 2024 by pyl3000
1
CUDA out of memory due to huge memory allocation request bug 🐞 Something isn't working
#18767 opened Oct 13, 2024 by pxanthopoulos
@PhaneeshB @AmosLewis
5
Some friction when using Rye/uv for package management. bindings/python Python wrapping IREE's C API bug 🐞 Something isn't working infrastructure Relating to build systems, CI, or testing
#18761 opened Oct 11, 2024 by benjamin-macadam
[ROCM] Evaluate whether we can attach amdgpu-no-implicitarg-ptr to our generated functions. codegen/rocm ROCm code generation compiler backend (HIP/HSA) performance ⚡ Performance/optimization related work across the compiler and runtime
#18760 opened Oct 11, 2024 by benvanik
Robustify upstream LICM for zero-trip count loops and other loop kinds enhancement ➕ New feature or request good first issue 🌱 Good for newcomers
#18759 opened Oct 11, 2024 by qedawkins
Better error message when device not found enhancement ➕ New feature or request
#18749 opened Oct 10, 2024 by renxida
5
Numeric issues on AMDGPU with f32 elementwise mul + f16 trunc
#18746 opened Oct 10, 2024 by nirvedhmeshram
2
[GlobalOptimization] 1x1 filter convolutions not converted to matmul
#18710 opened Oct 7, 2024 by Max191
1
@IanWood1
3
stablehlo.sort not working correctly on Metal bug 🐞 Something isn't working codegen/spirv SPIR-V code generation compiler backend hal/metal Runtime Apple Metal HAL backend integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#18698 opened Oct 4, 2024 by polvalente
1
onnx.Pad with mode 'reflect' fails to compile bug 🐞 Something isn't working integrations/onnx ONNX integration work
#18695 opened Oct 4, 2024 by giacs-epic
error: One or more operations with large vector sizes (8192 bytes) were found: bug 🐞 Something isn't working
#18677 opened Oct 3, 2024 by pdhirajkumarprasad
@pashu123
13
Build and publish Python 3.13 and 3.13t wheels bindings/python Python wrapping IREE's C API enhancement ➕ New feature or request infrastructure Relating to build systems, CI, or testing
#18652 opened Oct 1, 2024 by ScottTodd
@ScottTodd @marbre
6
[ROCM] TopK e2e test failing on MI250
#18649 opened Oct 1, 2024 by Max191
@krzysz00
1
ProTip! Mix and match filters to narrow down what you’re looking for.