[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)

Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

tests/entrypoints/pooling/reward/test_offline.py

@@ -36,6 +36,13 @@ def llm():
     cleanup_dist_env_and_memory()
 
 
+@pytest.mark.skip_global_cleanup
+def test_config(llm: LLM):
+    vllm_config = llm.llm_engine.vllm_config
+    assert vllm_config.cache_config.enable_prefix_caching
+    assert vllm_config.scheduler_config.enable_chunked_prefill
+
+
 def test_pooling_params(llm: LLM):
     def get_outputs(use_activation):
         outputs = llm.reward(