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
[Misc] Fix path and python alias errors in disagg_prefill exmaples (#18919)
Jiaxin Shan committed
Jun 3, 2025 at 17:15 UTC
abd7df2fca570998693fa8c1ae39d83fb789ef27
1 file changed
+3
-3
examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_example_nixl.sh
+3
-3
@@ -33,7 +33,7 @@ check_num_gpus() {
33
34
ensure_python_library_installed() {
35
echo "Checking if $1 is installed..."
36
- python -c "import $1" > /dev/null 2>&1
36
+ python3 -c "import $1" > /dev/null 2>&1
37
if [ $? -ne 0 ]; then
38
if [ "$1" == "nixl" ]; then
39
echo "$1 is not installed. Please refer to https://github.com/ai-dynamo/nixl for installation."
@@ -121,8 +121,8 @@ main() {
121
echo "All servers are up. Starting benchmark..."
122
123
# begin benchmark
124
- cd ../../../benchmarks/
125
- python benchmark_serving.py --port 9000 --seed $(date +%s) \
124
+ cd ../../../../benchmarks/
125
+ python3 benchmark_serving.py --port 9000 --seed $(date +%s) \
126
--model meta-llama/Llama-3.1-8B-Instruct \
127
--dataset-name random --random-input-len 7500 --random-output-len 200 \
128
--num-prompts 200 --burstiness 100 --request-rate 3.6 | tee benchmark.log