A number of PRs fail in the same place (Unit Tests, python:i386), seemingly unrelated to the PR itself. This is blocking these PRs. Is someone investigating this?
The end of the failing log:
In file included from runtime.c:65:0:
../../src/runtime/crt/ndarray.c: In function 'TVMNDArray_Load':
../../src/runtime/crt/ndarray.c:95:21: warning: format '%ld' expects argument of type 'long int', but argument 3 has type 'int64_t {aka long long int}' [-Wformat=]
fprintf(stderr, "invalid DLTensor file format: data_byte_size=%ld, "
^
../../src/runtime/crt/ndarray.c:95:21: warning: format '%ld' expects argument of type 'long int', but argument 4 has type 'int64_t {aka long long int}' [-Wformat=]
TVM_NUM_THREADS=1 build/test_dynamic build/test_bundle.so build/test_data.bin build/test_output.bin build/test_graph.json build/test_params.bin
timing: 0.11 ms (create), 0.02 ms (set_input), 0.15 ms (run), 0.00 ms (get_output), 0.00 ms (destroy)
TVM_NUM_THREADS=1 build/test_dynamic build/test_bundle_c.so build/test_data.bin build/test_output.bin build/test_graph.json build/test_params.bin
Segmentation fault (core dumped)
Makefile:41: recipe for target 'test_dynamic' failed
make: *** [test_dynamic] Error 139
script returned exit code 2
Examples:
https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-5272/8/pipeline/152 https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-5276/6/pipeline/152 https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-5252/11/pipeline/152 https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-5282/7/pipeline/152