Pinned issues
Issues
- 1
How to add a new backend to onnx-mlir RISC-V?
#2824 opened by xysxs - 2
xlm-roberta and Mistral-7B take significant amounts of memory during compilation
#2821 opened by cjvolzka - 7
- 1
Dynamic backend tests on NNPA cause errors
#2817 opened by negiyas - 0
Hugging Face GPT2 models segfault on CPU
#2822 opened by cjvolzka - 3
Dynamic backend tests cause errors.
#2743 opened by negiyas - 3
- 0
Unable to compile ibm-granite/granite-3b-code-instruct
#2814 opened by cjvolzka - 0
- 0
- 0
- 0
Can't find the definition of getTragetType()
#2805 opened by chachaleo - 4
An issue in ConvertKrnlToAffine Pass used in PR#2756
#2773 opened by imaihal - 0
- 2
New ops associated with opset 20
#2675 opened by hamptonm1 - 0
How to compile dynamic library for backend riscv
#2802 opened by xysxs - 0
--nnpa-placement-heuristic fails on mobilenetv2-12 with Assertion `aM == bM && "expected M dims to be identical"
#2800 opened by cjvolzka - 16
Compiling bidaf-9.onnx takes 170GB of memory
#2722 opened by cjvolzka - 1
Output of roberta models varies between NNPA compiles
#2789 opened by cjvolzka - 1
Update onnx.DFT to be compatible with Opset 20
#2670 opened by hamptonm1 - 9
Performance degradation in Models running on NNPA
#2769 opened by cjvolzka - 4
Any way to obtain a BUILD.overlay file for onnx-mlir?
#2771 opened by MbjYjbpivj - 1
bidaf-9.onnx from onnx model zoo fails to compile
#2770 opened by cjvolzka - 4
check-onnx-backend-numerical-nnpa fails following #2735
#2749 opened by cjvolzka - 1
Support Opset20 for ConstantOfShape
#2729 opened by cjvolzka - 1
Support Opset20 for ReduceMin/Max
#2728 opened by cjvolzka - 2
Dynamic backend tests failure in IndexExpr
#2755 opened by mikeessen - 0
Support Dynamic Dimensions for DFT Opset 20
#2752 opened by hamptonm1 - 3
Backend tests with the "force-dynamic" mode are not executed by "cmake check-onnx-backend-dynamic"
#2639 opened by negiyas - 0
DequantizeLinear/QuantizeLinear lowering
#2742 opened by SerenaC94 - 2
- 3
bertsquad-10 and 12 NNPA performance regression
#2633 opened by cjvolzka - 6
NNPA Accuracy Regression in candy-9 and mosaic-9
#2632 opened by cjvolzka - 1
LLVM ERROR: SmallVector unable to grow.
#2693 opened by cjvolzka - 1
Segfault when running inference with the IBM granite.20B model (the one with KV cache) at the number of input tokens of at least 1265
#2713 opened by tungld - 0
Provide Wheel files for PyRuntime artifacts?
#2711 opened by tehbone - 3
DequantLinear Operator output is fp32 or fp16?
#2701 opened by lingHu-123 - 1
OpenMP in the support libraries
#2705 opened by AlexandreEichenberger - 3
About a few error messages related to MAXF/MINF promoted in building the source code of onnx-mlir(0.4.2) in Ubuntu22.04.
#2696 opened by xwentian2020 - 0
Upgrade protobuf to 25.x
#2691 opened by cjvolzka - 2
Regarding the issues with ONNXMaxPoolSingleOutOp lower
#2683 opened by 2drag0n - 9
- 2
Reduced precision floating point issues
#2686 opened by hamptonm1 - 2
OpenMP with 2 models in a single process.
#2682 opened by AlexandreEichenberger - 4
Failed Test Sequence_with_dealloc
#2667 opened by Connor-XY - 4
Model Zoo Report is empty
#2672 opened by tungld - 13
Investigate why the check-onnx-backend-numerical-nnpa tests fail with multithreading
#2666 opened by hamptonm1 - 2
- 0
onnx-mlir --parallel issue
#2637 opened by robben225 - 1
Krnl.global and Krnl.entry_point() to llvm
#2630 opened by hm123450