xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:44:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Nixl integration tests DP-EP (#27199)

Browse Source 
Signed-off-by: NickLucche <nlucches@redhat.com>
This commit is contained in:
Nicolò Lucchesi 2025-10-22 05:17:48 +02:00 committed by GitHub
parent 265ecb05fb
commit bfa59be8f1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
tests/v1/kv_connector/nixl_integration/run_accuracy_test.sh
View File

@ -178,8 +178,16 @@ run_tests_for_model() {
--port $PORT \
--enforce-eager \
--gpu-memory-utilization $GPU_MEMORY_UTILIZATION \
--tensor-parallel-size $DECODER_TP_SIZE \
--kv-transfer-config '$KV_CONFIG'"
# DP-EP attention mode
if [[ -z "$DP_EP" ]]; then
BASE_CMD="${BASE_CMD} --tensor-parallel-size $DECODER_TP_SIZE"
else
echo "DP-EP Attention enabled, deploying with dp=DECODER_TP_SIZE and tp=1"
BASE_CMD="${BASE_CMD} --data-parallel-size $DECODER_TP_SIZE \
--tensor-parallel-size 1 --enable-expert-parallel"
fi
if [ -n "$model_args" ]; then
FULL_CMD="$BASE_CMD $model_args"

1
tests/v1/kv_connector/nixl_integration/tp_config_sweep_accuracy_test.sh
View File

@ -10,6 +10,7 @@ configs=(
"GPU_MEMORY_UTILIZATION=0.6 PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2"
"GPU_MEMORY_UTILIZATION=0.8 MODEL_NAMES=deepseek-ai/deepseek-vl2-tiny" # MLA case
"GPU_MEMORY_UTILIZATION=0.8 PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2 MODEL_NAMES=deepseek-ai/deepseek-vl2-tiny"
"DP_EP=1 GPU_MEMORY_UTILIZATION=0.8 PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2 MODEL_NAMES=deepseek-ai/deepseek-vl2-tiny" # MLA+P-TP1, D-DPEP=2 (TP=1)
)
run_tests() {