EngineX-Mthreads/enginex-mthreads-vllm
4
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Sync from v0.13

Browse Source
This commit is contained in:
xiezhongtao
2026-01-19 10:38:50 +08:00
parent b2ef04d792
commit 5aef6c175a
3714 changed files with 854317 additions and 89342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/offline_inference/disaggregated-prefill-v1/run.sh Normal file
View File

@@ -0,0 +1,11 @@
rm -rf local_storage/
if [ -f "output.txt" ]; then
rm output.txt
fi
# The directory of current script
SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 "$SCRIPT_DIR/prefill_example.py"
VLLM_ENABLE_V1_MULTIPROCESSING=0 CUDA_VISIBLE_DEVICES=0 python3 "$SCRIPT_DIR/decode_example.py"