[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/embed/test_offline.py

@@ -42,7 +42,7 @@ def llm():
 
 
 @pytest.mark.skip_global_cleanup
-def test_encode_api(llm: LLM):
+def test_token_embed(llm: LLM):
     outputs = llm.encode(prompts, pooling_task="token_embed", use_tqdm=False)
     multi_vector = outputs[0].outputs.data
     assert multi_vector.shape == (11, 384)