Skip to content

test: Fix L0_openai--trtllm #8543

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
Nov 25, 2025
Merged

test: Fix L0_openai--trtllm #8543

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
12 changes: 10 additions & 2 deletions qa/L0_openai/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,9 @@ function prepare_tensorrtllm() {
MODEL_REPO="$2"
ENGINE_PATH="$3"
TENSORRTLLM_DIR="$4"
TRITON_BACKEND=tensorrtllm
XGRAMMAR_TOKENIZER_INFO_PATH=tokenizer_info/${MODEL}/xgrammar_tokenizer_info.json
GUIDED_DECODING_BACKEND=xgrammar

mkdir -p ${MODEL_REPO}
cp ${TENSORRTLLM_DIR}/triton_backend/all_models/inflight_batcher_llm/* "${MODEL_REPO}" -r
Expand All @@ -83,12 +86,17 @@ function prepare_tensorrtllm() {
# 1. Generate the model's trt engines
python3 ../generate_engine.py --model "${MODEL}" --engine_path "${ENGINE_PATH}"

# 2. Prepare model repository
# 2. Generate the model's xgrammar tokenizer info. In order to run on C++ backend, we need an extra step to extract tokenizer’s information into json format.
XGRAMMAR_TOKENIZER_INFO_DIR=tokenizer_info/${MODEL}
rm -rf ${XGRAMMAR_TOKENIZER_INFO_DIR}
python3 /app/examples/generate_xgrammar_tokenizer_info.py --model_dir ${MODEL} --output_dir ${XGRAMMAR_TOKENIZER_INFO_DIR}

# 3. Prepare model repository
FILL_TEMPLATE="/app/tools/fill_template.py"
python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/preprocessing/config.pbtxt tokenizer_dir:${ENGINE_PATH},triton_max_batch_size:64,preprocessing_instance_count:1,max_queue_size:0
python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/postprocessing/config.pbtxt tokenizer_dir:${ENGINE_PATH},triton_max_batch_size:64,postprocessing_instance_count:1
python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm_bls/config.pbtxt triton_max_batch_size:64,decoupled_mode:True,bls_instance_count:1,accumulate_tokens:False,logits_datatype:TYPE_FP32,prompt_embedding_table_data_type:TYPE_FP16
python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm/config.pbtxt triton_backend:tensorrtllm,triton_max_batch_size:64,decoupled_mode:True,max_beam_width:1,engine_dir:${ENGINE_PATH},batching_strategy:inflight_fused_batching,max_queue_size:0,max_queue_delay_microseconds:1000,encoder_input_features_data_type:TYPE_FP16,logits_datatype:TYPE_FP32,exclude_input_in_output:True,prompt_embedding_table_data_type:TYPE_FP16
python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm/config.pbtxt triton_backend:${TRITON_BACKEND},triton_max_batch_size:64,decoupled_mode:True,max_beam_width:1,engine_dir:${ENGINE_PATH},batching_strategy:inflight_fused_batching,max_queue_size:0,max_queue_delay_microseconds:1000,encoder_input_features_data_type:TYPE_FP16,logits_datatype:TYPE_FP32,exclude_input_in_output:True,prompt_embedding_table_data_type:TYPE_FP16,guided_decoding_backend:${GUIDED_DECODING_BACKEND},xgrammar_tokenizer_info_path:${XGRAMMAR_TOKENIZER_INFO_PATH}
}

function pre_test() {
Expand Down
Loading