Update docker images to upgrade CUDNN from 9.5 to 9.6 #23244
+38
−32
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
snnn
changed the title
|
@tianleiwu , there is a strange error from CUDNN frontend , which was caused by upgrading CUDNN from 9.5 to 9.6. Could you please help me take a look? |
Tried upgrade both cudnn-frontend and cudnn, and submitted a test build: https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=1579205&view=results Worst case is that we may add an fallback to cudnn backend directly as before for the case that cannot be handled by cudnn frontend. |
|
The error was: [E:onnxruntime:yolov3, sequential_executor.cc:505 ExecuteKernel] Non-zero status code returned while running Conv node. Name:'conv2d_2_0' Status Message: Failed to initialize CUDNN Frontend/onnxruntime_src/onnxruntime/core/providers/cuda/cudnn_fe_call.cc:99 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cudnn_frontend::error_object; bool THRW = true; SUCCTYPE = cudnn_frontend::error_code_t; std::conditional_t<THRW, void, common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cudnn_fe_call.cc:91 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, SUCCTYPE, const char*, const char*, int) [with ERRTYPE = cudnn_frontend::error_object; bool THRW = true; SUCCTYPE = cudnn_frontend::error_code_t; std::conditional_t<THRW, void, common::Status> = void] CUDNN_FE failure 8: HEURISTIC_QUERY_FAILED ; GPU=0 ; hostname=98d137446008 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/nn/conv.cc ; line=225 ; expr=s_.cudnn_fe_graph->create_execution_plans({heur_mode}); |
@gedoensmax, @JTischbein, is it a known issue that cudnn 9.6 has regression of support convolution for yolo v3? Here is cudnn 9.6 debug log: |
snnn
force-pushed
the
snnn/update_docker_images
branch
from
c9c52e1 to
5944339
Compare
…oft/onnxruntime into snnn/update_docker_images
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The CUDNN in the Linux docker images have been upgraded from 9.5.1 to 9.6.0.