[Bugfix][v1] Fix step pooler implementation and step pooling usage in v1 (#19956)

Signed-off-by: Isotr0py <2037008807@qq.com>
2025-06-24 02:38:06 +08:00
parent 68aaeb3749
commit 61f4fc5dc6
14 changed files with 164 additions and 40 deletions
--- a/tests/quantization/test_bitsandbytes.py
+++ b/tests/quantization/test_bitsandbytes.py
@@ -161,7 +161,7 @@ def test_4bit_bnb_embedding_model(
                     dtype=dtype,
                     gpu_memory_utilization=0.5,
                     quantization="bitsandbytes") as vllm_model:
-        vllm_outputs = vllm_model.encode(example_prompts)
+        vllm_outputs = vllm_model.embed(example_prompts)
    check_embeddings_close(
        embeddings_0_lst=hf_outputs,
        embeddings_1_lst=vllm_outputs,