Error Codes¶
Compile-time error codes¶
This section details compile-time error codes you may encounter when using the RBLN SDK, specifically with the rebel-compiler
and optimum-rbln
tools. These errors occur during model compilation for the RBLN NPU, and understanding them aids in diagnosing and fixing issues. For deeper insight into the compilation process, refer to the RBLN Compiler and RSD white papers.
The model compilation workflow consists of two primary stages, each encompassing specific steps:
- Computation Graph Generation: Converts the model into an intermediate representation (IR). Steps include:
Device Graph Conversion
Operation (Op) Fusion
- Computation Graph Optimization: Optimizes the IR for RBLN NPU execution. Steps include:
Multi-Device Splitting
Op Splitting and Grouping
Op Tiling
Op Scheduling
Bufferization
Memory Allocation
Dependency Analysis
Command Scheduling
Code Generation
The table below lists error codes, their associated compile steps, and descriptions:
Error Code | Related Compile Step | Description |
---|
Inference-time error codes¶
This section lists the inference-time error codes that you might encounter when loading a compiled model (.rbln file) or running inference. The prefix of each error code indicates the stage at which the error occurred.
LOADING_
: The error occurred while loading the .rbln file. This may indicate an issue while reading the file. Consider upgrading your rebel-compiler to the latest version and recompiling your model.INIT_
: The error occurred while initializing the model.RUN_
: The error occurred while running inference.SYS_
: The error was initiated by the NPU device.
Error Code | Description | Possible Solutions |
---|---|---|
LOADING_FAILED | Unexpected error occurred while loading the compiled model (.rbln file). | Try re-compiling the model with the latest version of the compiler. |
LOADING_FILE_NOT_FOUND | The file does not exist at the specified path. | Make sure that you gave the correct path to the .rbln file. |
LOADING_INVALID_FILE | The file is not a valid .rbln file. | Make sure that you gave the correct path to the .rbln file or try re-compiling the model with the latest version of the compiler. |
LOADING_UNEXPECTED_EOF | The file is not a valid .rbln file. The .rbln file may be truncated. | Make sure that you gave the correct path to the .rbln file or try re-compiling the model with the latest version of the compiler. |
LOADING_INVALID_VERSION | The compiled model is compiled with an incompatible compiler. | Try re-compiling the model with the latest version of the compiler or update your runtime to the latest version. |
LOADING_INVALID_FILE | The contents of the model seem inconsistent or invalid. | Try re-compiling the model with the latest version of the compiler. |
LOADING_INVALID_CHECKSUM | Failed to verify the checksum of the compiled model. The compiled model may be corrupted. | Try re-compiling the model with the latest version of the compiler. |
LOADING_INVALID_SHARED_OBJ | The file may be corrupted or the target architecture of the compiled model does not match to your current environment. | Try re-compiling the model with the latest version of the compiler for the target architecture. |
INIT_INTERNAL | Unexpected error occurred while initializing the device for the model. | |
INIT_INVALID_ARGUMENT | An invalid argument was provided during initialization. | |
INIT_ALREADY_CREATED | A runtime has already been created for the compiled model. | Try creating a runtime on a different NPU or reusing the existing one. |
INIT_FAILED_LOADING_SHARED_OBJ | Failed to load the compiled host operator modules. | |
INIT_SHARED_OBJ_NO_SYMBOL | Failed to initialize the host operator due to a missing symbol. | |
INIT_MEM_ALLOC_FAILED | Failed to allocate device memory. | |
RUN_INTERNAL | Unexpected error occurred while running the inference. | |
RUN_ERROR_FROM_OTHER_THREAD | This error may occur when using async runtime. An error occurred from another thread and the run was thus aborted. | |
SYS_ERROR | An unexpected system-level error has occurred. | |
SYS_BUSY | The operation is still in progress, but a timeout occurred due to the user-specified timeout. | Try again with a longer timeout. Please refer to the timeout parameter of Runtime class. |
SYS_KERNEL_TIMEOUT | The operation on the device exceeded the kernel-specified timeout. (Default is 6 seconds.) | |
SYS_TASK_ABORTED | An error occurred during the execution of a task on the device. | |
SYS_ENOENT | No enabled system device. | |
SYS_ESRCH | No such process. | |
SYS_EINTR | Interrupted system call. | |
SYS_EIO | I/O error. | |
SYS_ENXIO | No such device or address. | |
SYS_ENOMEM | Out of memory. | |
SYS_EBUSY | Lack of device memory. | |
SYS_ENODEV | No such device. | |
SYS_ENOSPC | No space left on device. | |
SYS_EPIPE | Broken pipe. | |
SYS_ECANCELLED | Operation cancelled. |