A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 07:15 UTC
add an absolute path for run.sh (#18258)
Signed-off-by: calvin chen <120380290@qq.com>
Calvin Chen committed
Jun 3, 2025 at 03:38 UTC
c57d577e8dc41f270a3ce0d604f5d8ac51b08ed7
1 file changed
+9
-3
examples/offline_inference/disaggregated-prefill-v1/run.sh
+9
-3
@@ -1,5 +1,11 @@
1
rm -rf local_storage/
2
-rm output.txt
2
4
-VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 prefill_example.py
5
-VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 decode_example.py
3
+if [ -f "output.txt" ]; then
4
+ rm output.txt
5
+fi
6
+
7
+# The directory of current script
8
+SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
9
+
10
+VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 "$SCRIPT_DIR/prefill_example.py"
11
+VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 "$SCRIPT_DIR/decode_example.py"