diff --git a/tests/v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh b/tests/v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh index c7e6597200..a34f07edc9 100755 --- a/tests/v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh +++ b/tests/v1/kv_connector/nixl_integration/run_mamba_prefix_cache_test.sh @@ -51,6 +51,7 @@ vllm serve $MODEL \ --trust-remote-code \ --enable-prefix-caching \ --mamba-cache-mode all \ + --attention-backend FLASHINFER \ --kv-transfer-config "$KV_CONFIG" & # Start decode instance @@ -68,6 +69,7 @@ vllm serve $MODEL \ --trust-remote-code \ --enable-prefix-caching \ --mamba-cache-mode all \ + --attention-backend FLASHINFER \ --kv-transfer-config "$KV_CONFIG" & echo "Waiting for prefill instance on port $PREFILL_PORT..."