Jetpack 5.1.2 Patch 2 #7217
Draft
Jetpack 5.1.2 Patch 2 #7217
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
* Fix the copyrights in the files * Fix ups
* Add checks for trt uint8 support * Unify trt uint8 support check
Gather more info on execution.
* Add tolerance to cpu metrics test * set total memory to zero if not found in metrics output * Address comments, hardcode threshold, remove unnecessary verbosity
…or TRT data-dependent shape model (#5036) * Add generation script for TRT data-dependent shape model * Add test for TRT data dependent shape output * Fix generation script * Remove stale comment
* Add concurrent load speedup test * Add concurrent load unload test * Add checks for expected exception * Add concurrent load of same model test
* Add test for older OS modification time * Enhance documentation * Update documentation * Remove extra dashes
* Testing for windows build * Use different base container * Windows Dockerfile update * Revert some changes to resolve incorrect path issues Co-authored-by: Misha Chornyi <[email protected]>
* Use client repo to pull package name * Sed new package name * Generate Go stubs * Reminder to remove temp branch * Force removal, explain copying * Remove temp branch
* Set LD_PRELOAD * Install gperf and libgoogle-perftools-dev packages * Install gperf and libgoogle-perftools-dev packages for sdk container * Fix up for L0_client_build_variants * Add '--soname-synonyms' flag for valgrind tests * Install gperf and libgoogle-perftools-dev packages for benchmark tests * Fix up * Set TCMALLOC_RELEASE_RATE * Set LD_PRELOAD and TCMALLOC_RELEASE_RATE * Update comment * Set LD_PRELOAD properly. Increase server timeout * Update document for LD_PRELOAD usage * Unset LD_PRELOAD when running Valgrind tests * Revert server timeout Co-authored-by: Tanmay Verma <[email protected]>
* [DO NOT MERGE] * Remove Azure dependency in server component build * Finalize * Fix dependency * Fixing up * Clean up
* Add test for detecting S3 http2 upgrade request * Enhance testing * Copyright year update
* Add HPCX dependencies to search path * Copy hpcx to CPU-only container * Add ucc path to CPU-only image * Fixed if statement * Fix df variable * Combine hpcx LD_LIBRARY_PATH
* Add testing for Pytorch instance group kind MODEL * Remove unused item * Update testing to verify the infer result * Add copyright * Remove unused import * Update pip install * Update the model to use the same add sub logic * Add torch multi-gpu and multi-device models to L0_io * Fix up model version
* Be more specific with MPI removal * Delete all libmpi libs
* Update README.md for 23.06 * Update documentation structure * Update RELEASE.md Co-authored-by: Tanmay Verma <[email protected]> --------- Co-authored-by: Misha Chornyi <[email protected]> Co-authored-by: Tanmay Verma <[email protected]>
mc-nv
reviewed
May 14, 2024
rmccorm4
reviewed
May 14, 2024
rmccorm4
reviewed
May 14, 2024
nv-kmcgill53
approved these changes
May 14, 2024
rmccorm4
approved these changes
May 14, 2024
pvijayakrish
force-pushed
the
r23.06-update-2-jp
branch
from
45ae0a0 to
ecc425b
Compare
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.
Goal: Provide a PR to be used as a basis for review comments. This PR adds build functionality/testing to fix arbitrary file uploads via the model load API for the Jetpack 5.1.2 platform. Notably, it will package the version of libboost_filesystem.so.1.80.0 that was used to compile
tritonserverin a folder calledboost_filesystemalong with ourlib,bin, etc. folders.Note: This PR will not be merged. Please also note that the change to the lifecycle test simply removes all tests except the file override tests. This branch will be left around separately for users that want to build with this patch from source
Core changes: triton-inference-server/core#354