From ac3d748dba446b9a8417fe3005345c12989d8de0 Mon Sep 17 00:00:00 2001
From: Junichi Sato <junichi.sato@sbintuitions.co.jp>
Date: Wed, 30 Oct 2024 02:40:35 +0900
Subject: [PATCH] [Model]  Add LlamaEmbeddingModel as an embedding
 Implementation of LlamaModel (#9806)

---
 vllm/model_executor/models/registry.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/vllm/model_executor/models/registry.py b/vllm/model_executor/models/registry.py
index 32b9341a..30dfff31 100644
--- a/vllm/model_executor/models/registry.py
+++ b/vllm/model_executor/models/registry.py
@@ -95,6 +95,7 @@ _EMBEDDING_MODELS = {
     # [Text-only]
     "BertModel": ("bert", "BertEmbeddingModel"),
     "Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
+    "LlamaModel": ("llama", "LlamaEmbeddingModel"),
     "MistralModel": ("llama", "LlamaEmbeddingModel"),
     "Qwen2ForRewardModel": ("qwen2_rm", "Qwen2ForRewardModel"),
     "Qwen2ForSequenceClassification": (