Skip to content

Issues: openxla/iree

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

706 Open 2,166 Closed
706 Open 2,166 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Support Unaligned Matmul Shapes for CUDA Codegen codegen Shared code generation infrastructure and dialects enhancement ➕ New feature or request
#14116 opened Jun 14, 2023 by manishucsd
1
stablehlo.sort of i1 buffer fails post TypePropagation integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14115 opened Jun 14, 2023 by rsuderman JAX Integration Completeness
@NatashaKnk
LLVMCpuVectorization Fails with mixed FP-Int types for linalg.conv_1d_nwc_wcf integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14112 opened Jun 14, 2023 by rsuderman JAX Integration Completeness
4
VMConversion crashes with complex load for hal.buffer.load integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14111 opened Jun 14, 2023 by rsuderman JAX Integration Completeness
@benvanik
1
Upgrade GitHub Actions Runner to at least v2.305.0 by 2023-07-14 infrastructure Relating to build systems, CI, or testing
#14110 opened Jun 14, 2023 by GMNGeoffrey
IREE Compilation error for vulkan backend for Falcon bug 🐞 Something isn't working
#14109 opened Jun 14, 2023 by vivekkhandelwal1
@vivekkhandelwal1
1
Code generation features required to GEMM on Hopper GPU
#14106 opened Jun 14, 2023 by grypp
@grypp
1
vae.vmfb freezes on iree-benchmark-module bug 🐞 Something isn't working hal/metal Runtime Apple Metal HAL backend
#14104 opened Jun 14, 2023 by Ranvirsv
@antiagainst
chlo.topk lowering to iree_linalg_ext.topk does not handle uint types correctly integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14098 opened Jun 13, 2023 by rsuderman JAX Integration Completeness
@NatashaKnk
Compiler API: implement linking with installed-LLVM compiler/api IREE's public C compiler API and iree-compile-module tools
#14086 opened Jun 13, 2023 by bjacob
1
Failure when generating vector.shape_cast: source/result number of elements must match integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14079 opened Jun 13, 2023 by rsuderman JAX Integration Completeness
2
flow.dispatch.workgroup_count_from_slice surviving due to 0-element tensors. integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14077 opened Jun 12, 2023 by rsuderman JAX Integration Completeness
@benvanik @MaheshRavishankar
15
stablehlo.convolution fails during padding when using complex types integrations/stablehlo StableHLO (JAX/TensorFlow/etc) import and conversion
#14072 opened Jun 12, 2023 by rsuderman JAX Integration Completeness
Support non-mappable buffers in the python bindings and tests. bindings/python Python wrapping IREE's C API
#14071 opened Jun 12, 2023 by benvanik
@benvanik @stellaraccident
[Regression] Large models taking more than an hour to build bug 🐞 Something isn't working regression Marks regression of feature, compatibility or performance release-blocker Issue serious enough to stop promotion of release to Stable
#14067 opened Jun 12, 2023 by mariecwhite
21
[metal] Improve Metal HAL driver implementation hal/metal Runtime Apple Metal HAL backend
#14050 opened Jun 11, 2023 by antiagainst
@antiagainst
[metal] Make staging buffer robust to multithreading and async hal/metal Runtime Apple Metal HAL backend
#14049 opened Jun 11, 2023 by antiagainst
[metal] Probe metal offline toolchain in PATH hal/metal Runtime Apple Metal HAL backend
#14048 opened Jun 11, 2023 by antiagainst
[metal] Improve kernel compilation and pipeline creation hal/metal Runtime Apple Metal HAL backend
#14047 opened Jun 11, 2023 by antiagainst
@antiagainst
Some tests fail if IREE is configured with some default backends disabled.
#14034 opened Jun 9, 2023 by bjacob
@bjacob
2
Reuse Tracy macros for console output enhancement ➕ New feature or request quality of life 😊 Nice things are nice; let's have some
#14032 opened Jun 9, 2023 by okkwon
@benvanik @ScottTodd
Add initial support for GPU ukernels. codegen/nvvm NVVM code generation compiler backend
#14028 opened Jun 9, 2023 by benvanik
1
@benvanik @MaheshRavishankar
16
iree_bytecode_module passes --iree-llvmcpu- flags regardless of target backends cleanup 🧹 infrastructure Relating to build systems, CI, or testing
#14027 opened Jun 9, 2023 by bjacob
BF16 <= BF16 * I8 + F32
#14025 opened Jun 9, 2023 by qcolombet
@qcolombet
2
Track the performance of tensor.pad with the dispatch profiler enhancement ➕ New feature or request infrastructure/benchmark Relating to benchmarking infrastructure
#14021 opened Jun 9, 2023 by qcolombet
@manishucsd
ProTip! Mix and match filters to narrow down what you’re looking for.