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 17, 08:00 UTC
Compatible with Decapoda Research llama hf version (#251)
BasicCoder committed
Jun 27, 2023 at 00:23 UTC
471a7a456667971721a1ce589029fc82be6ab193
1 file changed
+1
vllm/model_executor/model_loader.py
+1
@@ -16,6 +16,7 @@ _MODEL_REGISTRY = {
16
"GPTBigCodeForCausalLM": GPTBigCodeForCausalLM,
17
"GPTNeoXForCausalLM": GPTNeoXForCausalLM,
18
"LlamaForCausalLM": LlamaForCausalLM,
19
+ "LLaMAForCausalLM": LlamaForCausalLM,
20
"OPTForCausalLM": OPTForCausalLM,
21
}
22