Fix TensorRT-LLM #7142
Merged
Fix TensorRT-LLM #7142
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
Tabrizian
previously approved these changes
Apr 20, 2024
| @@ -1708,6 +1708,30 @@ def tensorrtllm_prebuild(cmake_script): | |||
| # Export the TRT_ROOT environment variable | |||
| cmake_script.cmd("export TRT_ROOT=/usr/local/tensorrt") | |||
| cmake_script.cmd("export ARCH=$(uname -m)") | |||
| cmake_script.cmd( | |||
| 'export LD_LIBRARY_PATH="/usr/local/cuda/compat/lib.real:${LD_LIBRARY_PATH}"' | |||
There was a problem hiding this comment.
Because libcuda.so.1 can't be resolved till --runtime=nvidia is passed.
It's a workaround that allows us refer to the links in build container, can be deprecated in future.
You can create task and assign to me.
krishung5
reviewed
Apr 22, 2024
krishung5
reviewed
Apr 22, 2024
* Enable TensorRT-LLM build outside of CMake * TensorRT-LLM requires lower version of cuDNN
krishung5
approved these changes
Apr 23, 2024
mc-nv
added a commit
that referenced
this pull request
Apr 25, 2024
* TRT-LLM build * Update versions * Remove statment, as unused * Remove cache * add cmake option to set CXX11 ABI * Mchornyi krish 24.04 (#7149) * Enable TensorRT-LLM build outside of CMake * TensorRT-LLM requires lower version of cuDNN * Format --------- Co-authored-by: krishung5 <[email protected]>
mc-nv
added a commit
that referenced
this pull request
Apr 25, 2024
* TRT-LLM build * Update versions * Remove statment, as unused * Remove cache * add cmake option to set CXX11 ABI * Mchornyi krish 24.04 (#7149) * Enable TensorRT-LLM build outside of CMake * TensorRT-LLM requires lower version of cuDNN * Format --------- Co-authored-by: krishung5 <[email protected]>
mc-nv
added a commit
that referenced
this pull request
Apr 30, 2024
* Fix TensorRT-LLM (#7142) * TRT-LLM build * Update versions * Remove statment, as unused * Remove cache * add cmake option to set CXX11 ABI * Mchornyi krish 24.04 (#7149) * Enable TensorRT-LLM build outside of CMake * TensorRT-LLM requires lower version of cuDNN * Format --------- Co-authored-by: krishung5 <[email protected]> * Update README and versions for 2.45.0 / 24.04 (#7096) * Update README and versions for 2.45.0 / 24.04 * Update ONNX Runtime version - 1.17.3 --------- Co-authored-by: krishung5 <[email protected]>
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.
No description provided.