From dc148dc4d7633f749409f4b724a25669fd455d3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicol=C3=B2=20Lucchesi?= Date: Tue, 30 Jun 2026 17:14:13 +0200 Subject: [PATCH] [CI][Bugfix] Fix `Hybrid SSM NixlConnector PD prefix cache test (2 GPUs)` (#47157) Signed-off-by: NickLucche --- .../nixl_integration/run_mamba_prefix_cache_test.sh | 2 ++ 1 file changed, 2 insertions(+) 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..."