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, 06:45 UTC
Add `MptForCausalLM` key in model_loader (#1526)
Wenfei Yan committed
Oct 31, 2023 at 15:46 UTC
cf8849f2d6ea0a6ab76c94d2f585e02aea9e1512
1 file changed
+2
vllm/model_executor/model_loader.py
+2
@@ -27,6 +27,8 @@ _MODEL_REGISTRY = {
27
"LlamaForCausalLM": LlamaForCausalLM,
28
"LLaMAForCausalLM": LlamaForCausalLM, # For decapoda-research/llama-*
29
"MistralForCausalLM": MistralForCausalLM,
30
+ # transformers's mpt class has lower case
31
+ "MptForCausalLM": MPTForCausalLM,
32
"MPTForCausalLM": MPTForCausalLM,
33
"OPTForCausalLM": OPTForCausalLM,
34
"QWenLMHeadModel": QWenLMHeadModel,