microsoft / microsoft/onnxruntime
[Feature Request] 2024-05-09 07:05:28.107324198 [E:onnxruntime:Default, cann_call.cc:139 CannCall] CANNGRAPH failure -1: GRAPH_FAILED ; NPU=0 ; hostname=d5624f2a4431 ; expr=ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph); 2024-05-09 07:05:28.108008819 [E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while running main_graph_12023255667024707207_0 node. Name:'CANNExecutionProvider_main_graph_12023255667024707207_0_0' Status
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the feature request
2024-05-09 07:05:28.107324198 [E:onnxruntime:Default, cann_call.cc:139 CannCall] CANNGRAPH failure -1: GRAPH_FAILED ; NPU=0 ; hostname=d5624f2a4431 ; expr=ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph);
2024-05-09 07:05:28.108008819 [E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while running main_graph_12023255667024707207_0 node. Name:'CANNExecutionProvider_main_graph_12023255667024707207_0_0' Status Message: CANN Graph error executing ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph)
### Describe scenario use case
2024-05-09 07:05:28.107324198 [E:onnxruntime:Default, cann_call.cc:139 CannCall] CANNGRAPH failure -1: GRAPH_FAILED ; NPU=0 ; hostname=d5624f2a4431 ; expr=ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph);
2024-05-09 07:05:28.108008819 [E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while running main_graph_12023255667024707207_0 node. Name:'CANNExecutionProvider_main_graph_12023255667024707207_0_0' Status Message: CANN Graph error executing ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph)
Contributor guide
Research direction
Start with the reported call sites, cann_call.cc:139 and sequential_executor.cc:516, and trace the CANNExecutionProvider path around ge::aclgrphParseONNXFromMem. Reproduce the GRAPH_FAILED result with the missing model and environment details identified from the issue, then determine the failing condition and add a regression test if the relevant test location is found. Done means the reported CANN graph error is resolved or its unsupported input is clearly diagnosed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100