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
Support ChatGLMForConditionalGeneration (#1932)
Co-authored-by: shujunhua1 <shujunhua1@jd.com>
dancingpipi committed
Dec 6, 2023 at 02:52 UTC
1d9b737e054ecbbf6250e0541b74d4e8ca668406
1 file changed
+1
vllm/model_executor/model_loader.py
+1
@@ -19,6 +19,7 @@ _MODEL_REGISTRY = {
19
"BaichuanForCausalLM": BaichuanForCausalLM, # baichuan-13b
20
"BloomForCausalLM": BloomForCausalLM,
21
"ChatGLMModel": ChatGLMForCausalLM,
22
+ "ChatGLMForConditionalGeneration": ChatGLMForCausalLM,
23
"FalconForCausalLM": FalconForCausalLM,
24
"GPT2LMHeadModel": GPT2LMHeadModel,
25
"GPTBigCodeForCausalLM": GPTBigCodeForCausalLM,