[Frontend] Separate pooling APIs in offline inference (#11129)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

examples/offline_inference_classification.py

@@ -0,0 +1,28 @@
+from vllm import LLM
+
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+
+# Create an LLM.
+# You should pass task="classify" for classification models
+model = LLM(
+    model="jason9693/Qwen2.5-1.5B-apeach",
+    task="classify",
+    enforce_eager=True,
+)
+
+# Generate logits. The output is a list of ClassificationRequestOutputs.
+outputs = model.classify(prompts)
+
+# Print the outputs.
+for prompt, output in zip(prompts, outputs):
+    probs = output.outputs.probs
+    probs_trimmed = ((str(probs[:16])[:-1] +
+                      ", ...]") if len(probs) > 16 else probs)
+    print(f"Prompt: {prompt!r} | "
+          f"Class Probabilities: {probs_trimmed} (size={len(probs)})")

examples/offline_inference_embedding.py

@@ -9,14 +9,20 @@ prompts = [
 ]
 
 # Create an LLM.
+# You should pass task="embed" for embedding models
 model = LLM(
     model="intfloat/e5-mistral-7b-instruct",
-    task="embed",  # You should pass task="embed" for embedding models
+    task="embed",
     enforce_eager=True,
 )
 
-# Generate embedding. The output is a list of PoolingRequestOutputs.
-outputs = model.encode(prompts)
+# Generate embedding. The output is a list of EmbeddingRequestOutputs.
+outputs = model.embed(prompts)
+
 # Print the outputs.
-for output in outputs:
-    print(output.outputs.embedding)  # list of 4096 floats
+for prompt, output in zip(prompts, outputs):
+    embeds = output.outputs.embedding
+    embeds_trimmed = ((str(embeds[:16])[:-1] +
+                       ", ...]") if len(embeds) > 16 else embeds)
+    print(f"Prompt: {prompt!r} | "
+          f"Embeddings: {embeds_trimmed} (size={len(embeds)})")

examples/offline_inference_scoring.py

@@ -0,0 +1,23 @@
+from vllm import LLM
+
+# Sample prompts.
+text_1 = "What is the capital of France?"
+texts_2 = [
+    "The capital of Brazil is Brasilia.", "The capital of France is Paris."
+]
+
+# Create an LLM.
+# You should pass task="score" for cross-encoder models
+model = LLM(
+    model="BAAI/bge-reranker-v2-m3",
+    task="score",
+    enforce_eager=True,
+)
+
+# Generate scores. The output is a list of ScoringRequestOutputs.
+outputs = model.score(text_1, texts_2)
+
+# Print the outputs.
+for text_2, output in zip(texts_2, outputs):
+    score = output.outputs.score
+    print(f"Pair: {[text_1, text_2]!r} | Score: {score}")

examples/offline_inference_vision_language_embedding.py

@@ -133,7 +133,7 @@ def run_encode(model: str, modality: QueryModality):
     if req_data.image is not None:
         mm_data["image"] = req_data.image
 
-    outputs = req_data.llm.encode({
+    outputs = req_data.llm.embed({
         "prompt": req_data.prompt,
         "multi_modal_data": mm_data,
     })