Compiler


What float-abi and fpu should be used for Raspberry Pi ARMv7l model so file? (4)
Array bounds checking (1)
How to support more arguments for customized pass (1)
What if deploy Clang/LLVM to compile the generated CUDA kernel? (3)
Resnet50_v2 for Mali Compilation - Cannot find config for target compilation (6)
From_onnx conversion issue with MatMul+Add (3)
[SOLVED] Nnvm from_mxnet resnet152 python3 - RecursionError: maximum recursion depth exceeded (3)
[Fixed]Dangerous optimization in simplify (3)
[SOLVED] Failed to cross compile resnet50_v1 for tvm.target.mali ARMv7 Mali GPU (3)
[SOLVED] Failed to compile models for ARMv7 Mali GPU with opt_level 3 (2)
Is there a diagram about how to visit each node of HalideIR? (1)
Signed_integer_overflow when batch size is large (2)
How can I get serialized HalideIR in tvm through c++ (3)
Problems of deploying models on Jetson TX2 (5)
Compiler Errors for PixelShuffle layer (16)
How does Relay handle while loop (5)
[AutoTVM][NNVM] error when extract_task_from_graph with opt_level=3 (17)
Support for Halide select operator (1)
Simplify if stmt within for (2)
C++ implementation of NN operations (7)
What options do affect number of CPU cores used? (3)
Nnvm_quick_start script error (2)
The Runtime Error about nnvm_quick_start.py (7)
Complication with cuda/cudnn/cublas/llvm enabled is not effective (1)
[AUTOTVM] Building SSD error (10)
[COMPILER][BUG] Can't cross compile OpenCL target without OpenCL device (2)
Expr in ArrayNode (4)
[Tensorize] Tensorize failed after reorder (1)
Unable to compile ResNet-18 with different input shape for CUDA target (2)
Halide::Internal::StmtNode<For> does not have stride attribute (3)