@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 471a7a4566
Fork 0

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