Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ci: Enable TF-TRT tests #7399

Merged
merged 5 commits into from
Jul 11, 2024
Merged

ci: Enable TF-TRT tests #7399

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5b35b69
Enable TF-TRT tests
pskiran1 Jun 25, 2024
1d234af
Test
pskiran1 Jun 27, 2024
c8115cb
Merge branch 'main' of https://github.com/triton-inference-server/ser…
pskiran1 Jul 1, 2024
09bae95
Merge branch 'main' of https://github.com/triton-inference-server/ser…
pskiran1 Jul 8, 2024
68ba45c
Merge branch 'r24.07' of https://github.com/triton-inference-server/s…
pskiran1 Jul 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions qa/L0_tftrt_optimization/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,8 +53,6 @@ source ../common/util.sh

RET=0

# FIXME [DLIS-6660] Update TF image models to support dynamic batching
# Currently, models cannot load with TF-TRT optimization due to the removal of implicit batch support in TensorRT v10 onwards
for MODEL in \
graphdef_float32_float32_float32 \
savedmodel_float32_float32_float32; do
Expand Down
4 changes: 0 additions & 4 deletions qa/L0_warmup/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,10 +288,6 @@ for BACKEND in ${BACKENDS}; do
fi

if [ "$BACKEND" == "graphdef" ]; then
# FIXME [DLIS-6660] Update TF image models to support dynamic batching
# Currently, models cannot load with TF-TRT optimization due to the removal of implicit batch support in TensorRT v10 onwards
continue

# Show effect of warmup by using a TF model with TF-TRT optimization which is
# known to be slow on first inference.
# Note: model can be obatined via the fetching script in docs/example
Expand Down
Loading