Skip to content

test: Fix L0_perf_tensorrt_llm (#8823) #8832

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

Merged
mc-nv merged 1 commit into from
Jun 11, 2026
Merged

test: Fix L0_perf_tensorrt_llm (#8823) #8832

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 6 additions & 3 deletions qa/L0_perf_tensorrt_llm/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#!/bin/bash
# Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
Expand Down Expand Up @@ -29,6 +29,7 @@ RET=0
BASE_DIR=$(pwd)
NUM_GPUS=${NUM_GPUS:=1}
TENSORRTLLM_BACKEND_REPO_TAG=${TENSORRTLLM_BACKEND_REPO_TAG:="main"}
TRITON_REPO_ORG=${TRITON_REPO_ORG:="https://github.com/triton-inference-server"}
TRT_ROOT="/usr/local/tensorrt"

MODEL_NAME="gpt2_tensorrt_llm"
Expand Down Expand Up @@ -76,6 +77,9 @@ function upgrade_openmpi {
}

# Update environment variables
export PATH=/opt/hpcx/ompi/bin:$PATH
export LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:$LD_LIBRARY_PATH

if ! grep -q '/opt/hpcx/ompi/bin' ~/.bashrc; then
echo 'export PATH=/opt/hpcx/ompi/bin:$PATH' >>~/.bashrc
fi
Expand All @@ -84,7 +88,6 @@ function upgrade_openmpi {
echo 'export LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:$LD_LIBRARY_PATH' >>~/.bashrc
fi
ldconfig
source ~/.bashrc
cd "$BASE_DIR"
mpirun --version
}
Expand All @@ -96,7 +99,7 @@ build_gpt2_tensorrt_engine
prepare_model_repository

# Install perf_analyzer
pip3 install tritonclient
pip3 install perf_analyzer

ARCH="amd64"
STATIC_BATCH=1
Expand Down
4 changes: 2 additions & 2 deletions qa/common/trtllm_util.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#!/bin/bash
# Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
Expand Down Expand Up @@ -53,7 +53,7 @@ function build_gpt2_tensorrt_engine {
trtllm-build --checkpoint_dir "./c-model/gpt2/${NUM_GPUS}-gpu/" \
--gpt_attention_plugin float16 \
--remove_input_padding enable \
--paged_kv_cache enable \
--kv_cache_type paged \
--gemm_plugin float16 \
--workers "${NUM_GPUS}" \
--output_dir "${ENGINES_DIR}"
Expand Down
Loading