You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
hello community,
trying T5 inference(https://developer.nvidia.com/blog/deploying-gpt-j-and-t5-with-fastertransformer-and-triton-inference-server/). getting below error on execution of this
I0517 04:22:59.609618 24895 libtorch.cc:1309] TRITONBACKEND_Initialize: pytorch
I0517 04:22:59.609747 24895 libtorch.cc:1319] Triton TRITONBACKEND API version: 1.8
I0517 04:22:59.609760 24895 libtorch.cc:1325] 'pytorch' TRITONBACKEND API version: 1.8
2023-05-17 04:22:59.844393: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
2023-05-17 04:22:59.907030: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
I0517 04:22:59.907125 24895 tensorflow.cc:2176] TRITONBACKEND_Initialize: tensorflow
I0517 04:22:59.907157 24895 tensorflow.cc:2186] Triton TRITONBACKEND API version: 1.8
I0517 04:22:59.907170 24895 tensorflow.cc:2192] 'tensorflow' TRITONBACKEND API version: 1.8
I0517 04:22:59.907181 24895 tensorflow.cc:2216] backend configuration:
{}
I0517 04:22:59.909302 24895 onnxruntime.cc:2319] TRITONBACKEND_Initialize: onnxruntime
I0517 04:22:59.909336 24895 onnxruntime.cc:2329] Triton TRITONBACKEND API version: 1.8
I0517 04:22:59.909349 24895 onnxruntime.cc:2335] 'onnxruntime' TRITONBACKEND API version: 1.8
I0517 04:22:59.909358 24895 onnxruntime.cc:2365] backend configuration:
{}
I0517 04:22:59.935877 24895 openvino.cc:1207] TRITONBACKEND_Initialize: openvino
I0517 04:22:59.935910 24895 openvino.cc:1217] Triton TRITONBACKEND API version: 1.8
I0517 04:22:59.935923 24895 openvino.cc:1223] 'openvino' TRITONBACKEND API version: 1.8
I0517 04:23:00.184609 24895 pinned_memory_manager.cc:240] Pinned memory pool is created at '0x7f275a000000' with size 268435456
I0517 04:23:00.185115 24895 cuda_memory_manager.cc:105] CUDA memory pool is created on device 0 with size 67108864
I0517 04:23:00.188362 24895 model_repository_manager.cc:997] loading: fastertransformer:1
I0517 04:23:00.411902 24895 libfastertransformer.cc:1226] TRITONBACKEND_Initialize: fastertransformer
I0517 04:23:00.411933 24895 libfastertransformer.cc:1236] Triton TRITONBACKEND API version: 1.8
I0517 04:23:00.411940 24895 libfastertransformer.cc:1242] 'fastertransformer' TRITONBACKEND API version: 1.8
I0517 04:23:00.411981 24895 libfastertransformer.cc:1274] TRITONBACKEND_ModelInitialize: fastertransformer (version 1)
I0517 04:23:00.415133 24895 libfastertransformer.cc:1320] TRITONBACKEND_ModelInstanceInitialize: fastertransformer_0 (device 0)
terminate called after throwing an instance of 'std::runtime_error'
what(): [FT][ERROR] shared_ft_model->getTensorParaSize() * shared_ft_model->getPipelineParaSize() == world_size Assertion fail: /workspace/build/fastertransformer_backend/src/libfastertransformer.cc:498
[01ed9ece5842:24895] *** Process received signal ***
[01ed9ece5842:24895] Signal: Aborted (6)
[01ed9ece5842:24895] Signal code: (-6)
[01ed9ece5842:24895] [ 0] /usr/lib/x86_64-linux-gnu/libpthread.so.0(+0x14420)[0x7f28b7a5d420]
[01ed9ece5842:24895] [ 1] /usr/lib/x86_64-linux-gnu/libc.so.6(gsignal+0xcb)[0x7f28b71e300b]
[01ed9ece5842:24895] [ 2] /usr/lib/x86_64-linux-gnu/libc.so.6(abort+0x12b)[0x7f28b71c2859]
[01ed9ece5842:24895] [ 3] /usr/lib/x86_64-linux-gnu/libstdc++.so.6(+0x9e911)[0x7f28b759c911]
[01ed9ece5842:24895] [ 4] /usr/lib/x86_64-linux-gnu/libstdc++.so.6(+0xaa38c)[0x7f28b75a838c]
[01ed9ece5842:24895] [ 5] /usr/lib/x86_64-linux-gnu/libstdc++.so.6(+0xaa3f7)[0x7f28b75a83f7]
[01ed9ece5842:24895] [ 6] /usr/lib/x86_64-linux-gnu/libstdc++.so.6(+0xaa6a9)[0x7f28b75a86a9]
[01ed9ece5842:24895] [ 7] /opt/tritonserver/backends/fastertransformer/libtriton_fastertransformer.so(+0x2a660)[0x7f27e608b660]
[01ed9ece5842:24895] [ 8] /opt/tritonserver/backends/fastertransformer/libtriton_fastertransformer.so(+0x1e45f)[0x7f27e607f45f]
[01ed9ece5842:24895] [ 9] /opt/tritonserver/backends/fastertransformer/libtriton_fastertransformer.so(+0x1fa02)[0x7f27e6080a02]
[01ed9ece5842:24895] [10] /opt/tritonserver/backends/fastertransformer/libtriton_fastertransformer.so(TRITONBACKEND_ModelInstanceInitialize+0x38c)[0x7f27e60832fc]
[01ed9ece5842:24895] [11] /opt/tritonserver/bin/../lib/libtritonserver.so(+0x30fece)[0x7f28b7d8dece]
[01ed9ece5842:24895] [12] /opt/tritonserver/bin/../lib/libtritonserver.so(+0x311493)[0x7f28b7d8f493]
[01ed9ece5842:24895] [13] /opt/tritonserver/bin/../lib/libtritonserver.so(+0x309147)[0x7f28b7d87147]
[01ed9ece5842:24895] [14] /opt/tritonserver/bin/../lib/libtritonserver.so(+0x18c37a)[0x7f28b7c0a37a]
[01ed9ece5842:24895] [15] /opt/tritonserver/bin/../lib/libtritonserver.so(+0x19a351)[0x7f28b7c18351]
[01ed9ece5842:24895] [16] /usr/lib/x86_64-linux-gnu/libstdc++.so.6(+0xd6de4)[0x7f28b75d4de4]
[01ed9ece5842:24895] [17] /usr/lib/x86_64-linux-gnu/libpthread.so.0(+0x8609)[0x7f28b7a51609]
[01ed9ece5842:24895] [18] /usr/lib/x86_64-linux-gnu/libc.so.6(clone+0x43)[0x7f28b72bf133]
[01ed9ece5842:24895] *** End of error message ***
Thanks in advance
Beta Was this translation helpful? Give feedback.
All reactions