Skip to content

Issues: iree-org/iree

Release tracker - 3.2.0
#19641 opened Jan 8, 2025 by ScottTodd
Open 1
Pending LLVM Dependent Patches
#15685 opened Nov 27, 2023 by stellaraccident
Open 5
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

1,081 Open 3,051 Closed
1,081 Open 3,051 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

Llama3.1_fp16_8b_tp8 fails prefill for long prompts when using async allocator bug 🐞 Something isn't working
#19812 opened Jan 24, 2025 by stbaione
[AMDGPU] iree-hal-hip-di SIGSEGV for llama 8b fp8 model bug 🐞 Something isn't working
#19809 opened Jan 24, 2025 by AmosLewis
Add a stream.tensor.dispatch op for encoding tensor types. cleanup 🧹 compiler/dialects Relating to the IREE compiler dialects (flow, hal, vm)
#19806 opened Jan 24, 2025 by benvanik
1
@benvanik @hanhanW
Spooky behavior causing segfaults on innocuous iree-run-module ONNX op test runs. bug 🐞 Something isn't working runtime Relating to the IREE runtime library
#19795 opened Jan 23, 2025 by benvanik
Enable tools to accept input args as IRPA files enhancement ➕ New feature or request runtime/tools IREE's runtime tooling (iree-run-module, iree-benchmark-module, etc)
#19783 opened Jan 23, 2025 by sogartar
1
Support for LiteRT (TensorFlow Lite, .tflite) with TOSA 1.0 integrations/tensorflow TensorFlow model import and conversion integrations/tosa Tensor Operator Set Architecture (TOSA) import, tests, etc.
#19777 opened Jan 23, 2025 by ScottTodd
1
[LLVMGPU] Scatter codegen fails on unaligned shapes bug 🐞 Something isn't working
#19760 opened Jan 22, 2025 by Groverkss
1
Scatter fusion support for llama
#19752 opened Jan 21, 2025 by IanWood1
1 of 4 tasks
@IanWood1
[PERF] [FLUX] Flux.1 Dev Transformer perf tracker codegen/rocm ROCm code generation compiler backend (HIP/HSA) codegen Shared code generation infrastructure and dialects performance ⚡ Performance/optimization related work across the compiler and runtime
#19751 opened Jan 21, 2025 by PhaneeshB
1
[LLVMCPU] Gather codegen for gather on strided access is numerically incorrect bug 🐞 Something isn't working
#19749 opened Jan 21, 2025 by Groverkss
3
What to do about fast-math? codegen/llvm LLVM code generation compiler backend codegen Shared code generation infrastructure and dialects performance ⚡ Performance/optimization related work across the compiler and runtime
#19743 opened Jan 20, 2025 by bjacob
1
[Tuner][Codegen] Make default tuning be available per-SKU instead of per-arch tuner
#19720 opened Jan 16, 2025 by kuhar
@bangtianliu
1
[GPU] [ROCM] Matmul-like op followed by pad produces NAN values bug 🐞 Something isn't working
#19703 opened Jan 15, 2025 by zjgarvey Scalability on AMD GPU
[codegen][gpu] Use HWFC filter layout for SDXL convolution Ops codegen/rocm ROCm code generation compiler backend (HIP/HSA)
#19701 opened Jan 14, 2025 by jerryyin
@jerryyin
5
(compile) (rocm) aggressive fusion issues with memref.copy contexts when lowering conv_2d_nhwc_hwcf bug 🐞 Something isn't working
#19688 opened Jan 13, 2025 by monorimet
3
Significant Compilation Time for Llama3.1 8b f16 with tensor-parallelism == 8 bug 🐞 Something isn't working
#19687 opened Jan 13, 2025 by stbaione
@IanWood1
12
GPUReduceBankConflicts does not keep track of shared memory usage good first issue 🌱 Good for newcomers help wanted Extra attention is needed
#19675 opened Jan 10, 2025 by nirvedhmeshram
[Tuner][Codegen] Allow for tuning specs to override codegen pipeline without setting full lowering config enhancement ➕ New feature or request tuner
#19674 opened Jan 10, 2025 by kuhar
4
Validate and optimize polynomial approximation of math functions enhancement ➕ New feature or request good first issue 🌱 Good for newcomers performance ⚡ Performance/optimization related work across the compiler and runtime
#19673 opened Jan 10, 2025 by kuhar
1
iree-test-deps fails to build on macos-14 bug 🐞 Something isn't working platform/macos 🍎 MacOS-specific build, execution, benchmarking, and deployment
#19664 opened Jan 10, 2025 by marbre
1
Custom CUDA dispatch sample broken bug 🐞 Something isn't working
#19662 opened Jan 10, 2025 by maxbartel
2
[GPU] Improve NCHW Convolution performance codegen/rocm ROCm code generation compiler backend (HIP/HSA) performance ⚡ Performance/optimization related work across the compiler and runtime
#19660 opened Jan 10, 2025 by qedawkins
3 tasks
Dispatch from llama2 lowering error. bug 🐞 Something isn't working
#19643 opened Jan 9, 2025 by bailuan
Release tracker - 3.2.0
#19641 opened Jan 8, 2025 by ScottTodd
6 tasks
1
Burndown list of HSA/ROCR issues for initial milestone hal/amdgpu Runtime AMDGPU HAL backend
#19636 opened Jan 8, 2025 by benvanik
11 tasks
@benvanik
1
ProTip! no:milestone will show everything without a milestone.