A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 09:30 UTC
[Model] Add LlamaEmbeddingModel as an embedding Implementation of LlamaModel (#9806)
Junichi Sato committed
Oct 30, 2024 at 02:40 UTC
ac3d748dba446b9a8417fe3005345c12989d8de0
1 file changed
+1
vllm/model_executor/models/registry.py
+1
@@ -95,6 +95,7 @@ _EMBEDDING_MODELS = {
95
# [Text-only]
96
"BertModel": ("bert", "BertEmbeddingModel"),
97
"Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
98
+ "LlamaModel": ("llama", "LlamaEmbeddingModel"),
99
"MistralModel": ("llama", "LlamaEmbeddingModel"),
100
"Qwen2ForRewardModel": ("qwen2_rm", "Qwen2ForRewardModel"),
101
"Qwen2ForSequenceClassification": (