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 14, 05:30 UTC
Adjusted the model order of the model registration file (#26798)
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
汪志鹏 committed
Oct 14, 2025 at 21:26 UTC
e9f1b8c9e9ab9dd659e95a43b38329f34a805281
1 file changed
+6
-6
vllm/model_executor/models/registry.py
+6
-6
@@ -60,9 +60,6 @@ _TEXT_GENERATION_MODELS = {
60
"AquilaForCausalLM": ("llama", "LlamaForCausalLM"), # AquilaChat2
61
"ArceeForCausalLM": ("arcee", "ArceeForCausalLM"),
62
"ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
63
- "MiniMaxForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
64
- "MiniMaxText01ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
65
- "MiniMaxM1ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
63
# baichuan-7b, upper case 'C' in the class name
64
"BaiChuanForCausalLM": ("baichuan", "BaiChuanForCausalLM"),
65
# baichuan-13b, lower case 'c' in the class name
@@ -87,8 +84,10 @@ _TEXT_GENERATION_MODELS = {
84
"Ernie4_5_MoeForCausalLM": ("ernie45_moe", "Ernie4_5_MoeForCausalLM"),
85
"ExaoneForCausalLM": ("exaone", "ExaoneForCausalLM"),
86
"Exaone4ForCausalLM": ("exaone4", "Exaone4ForCausalLM"),
90
- "FalconForCausalLM": ("falcon", "FalconForCausalLM"),
87
"Fairseq2LlamaForCausalLM": ("fairseq2_llama", "Fairseq2LlamaForCausalLM"),
88
+ "FalconForCausalLM": ("falcon", "FalconForCausalLM"),
89
+ "FalconMambaForCausalLM": ("mamba", "MambaForCausalLM"),
90
+ "FalconH1ForCausalLM": ("falcon_h1", "FalconH1ForCausalLM"),
91
"FlexOlmoForCausalLM": ("flex_olmo", "FlexOlmoForCausalLM"),
92
"GemmaForCausalLM": ("gemma", "GemmaForCausalLM"),
93
"Gemma2ForCausalLM": ("gemma2", "Gemma2ForCausalLM"),
@@ -126,11 +125,12 @@ _TEXT_GENERATION_MODELS = {
125
"LLaMAForCausalLM": ("llama", "LlamaForCausalLM"),
126
"LongcatFlashForCausalLM": ("longcat_flash", "LongcatFlashForCausalLM"),
127
"MambaForCausalLM": ("mamba", "MambaForCausalLM"),
129
- "FalconMambaForCausalLM": ("mamba", "MambaForCausalLM"),
130
- "FalconH1ForCausalLM": ("falcon_h1", "FalconH1ForCausalLM"),
128
"Mamba2ForCausalLM": ("mamba2", "Mamba2ForCausalLM"),
129
"MiniCPMForCausalLM": ("minicpm", "MiniCPMForCausalLM"),
130
"MiniCPM3ForCausalLM": ("minicpm3", "MiniCPM3ForCausalLM"),
131
+ "MiniMaxForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
132
+ "MiniMaxText01ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
133
+ "MiniMaxM1ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
134
"MistralForCausalLM": ("llama", "LlamaForCausalLM"),
135
"MixtralForCausalLM": ("mixtral", "MixtralForCausalLM"),
136
# transformers's mpt class has lower case