Sync from v0.13

examples/offline_inference/basic/embed.py

@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from argparse import Namespace
+
+from vllm import LLM, EngineArgs
+from vllm.attention.backends.registry import AttentionBackendEnum
+from vllm.config import AttentionConfig
+from vllm.platforms import current_platform
+from vllm.utils.argparse_utils import FlexibleArgumentParser
+
+
+def parse_args():
+    parser = FlexibleArgumentParser()
+    parser = EngineArgs.add_cli_args(parser)
+    # Set example specific arguments
+    parser.set_defaults(
+        model="intfloat/e5-small",
+        runner="pooling",
+        enforce_eager=True,
+    )
+    return parser.parse_args()
+
+
+def main(args: Namespace):
+    if current_platform.is_rocm():
+        args.attention_config = AttentionConfig(
+            backend=AttentionBackendEnum.FLEX_ATTENTION
+        )
+
+    # 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 runner="pooling" for embedding models
+    llm = LLM(**vars(args))
+
+    # Generate embedding. The output is a list of EmbeddingRequestOutputs.
+    outputs = llm.embed(prompts)
+
+    # Print the outputs.
+    print("\nGenerated Outputs:\n" + "-" * 60)
+    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} \nEmbeddings: {embeds_trimmed} (size={len(embeds)})")
+        print("-" * 60)
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)