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 16, 19:30 UTC
Add Nemotron to PP_SUPPORTED_MODELS (#6863)
Michael Goin committed
Jul 27, 2024 at 18:05 UTC
b1366a953498fde9c5e7ab91915367ebc69008b2
1 file changed
+1
vllm/config.py
+1
@@ -39,6 +39,7 @@ _PP_SUPPORTED_MODELS = [
39
"Phi3ForCausalLM",
40
"GPT2LMHeadModel",
41
"MixtralForCausalLM",
42
+ "NemotronForCausalLM",
43
]
44
45