Update README.md

README.md

@@ -92,6 +92,7 @@ On LMEB, reranking models demonstrate a clear advantage, with even the 0.27B Nan
 ![lmeb_emb](./assets/lmeb_emb.jpg)
 
 # Usage
+## Using transformers
 ```python
 import argparse
 from typing import Optional
@@ -204,6 +205,64 @@ rankings: [{'corpus_id': 0, 'score': 0.9998205304145813}, {'corpus_id': 1, 'scor
 
 ```
 
+## Using vLLM
+An experimental single-GPU adapter is available for offline
+`LLM.classify()` reranking and optional FastAPI serving. It reuses the original
+checkpoint without adding or modifying model weights.
+
+The adapter has been validated with Python 3.12, vLLM 0.19.1, Transformers
+5.6.2 and CUDA BF16:
+
+```bash
+conda create -n kalm-vllm python=3.12 -y
+conda activate kalm-vllm
+pip install "vllm==0.19.1" "transformers==5.6.2"
+
+hf download KaLM-Embedding/KaLM-Reranker-V1-Nano \
+  --local-dir ./KaLM-Reranker-V1-Nano
+pip install ./KaLM-Reranker-V1-Nano/vllm_support --no-deps
+export VLLM_PLUGINS=kalm_t5gemma2
+```
+
+Offline Python:
+
+```python
+from kalm_t5gemma2_vllm_plugin import KaLMVLLMReranker
+
+query = "What is the capital of China?"
+documents = [
+    "The capital of China is Beijing.",
+    "Gravity attracts bodies toward one another.",
+]
+
+with KaLMVLLMReranker(
+    "KaLM-Embedding/KaLM-Reranker-V1-Nano",
+    query_max_length=512,
+    document_max_length=1024,
+    encoder_chunk_size=4,
+) as reranker:
+    print(reranker.rank(query, documents))
+```
+
+Offline CLI and online service:
+
+```bash
+kalm-vllm-rerank --return-margin
+
+pip install "fastapi>=0.136,<0.137" "uvicorn>=0.46,<0.47"
+kalm-vllm-serve --host 0.0.0.0 --port 8000
+kalm-vllm-client --endpoint rerank --return-margin
+```
+
+The default output is `P(yes)`. Set `return_margin=true` to also receive
+`yes_logit - no_logit`. The supported encoder chunk sizes are
+`1, 2, 4, 8, 16, 32`, with `4` as the default.
+
+This adapter uses vLLM's plugin, scheduling and pooling interfaces while the
+T5Gemma2 semantic forward still runs through Transformers. It is not vLLM's
+native HTTP `/score` implementation or a complete vLLM-native kernel port.
+See [the complete installation, API and troubleshooting guide](./vllm_support/README.md).
+
 # Acknowledgements
 We sincerely thank `jina-reranker-v3` and `Qwen3-Reranker` for their valuable inspiration and contributions to the reranking community, from which we have learned a lot.