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 15, 14:45 UTC
[Bugfix] clean up duplicated code (#16485)
Signed-off-by: Gogs <gogs@fake.local> Co-authored-by: Gogs <gogs@fake.local>
rongfu.leng committed
Apr 12, 2025 at 07:19 UTC
56c76c2e0ea174faff3422dfc6733a2c2e7c7444
1 file changed
-1
vllm/model_executor/models/opt.py
-1
@@ -324,7 +324,6 @@ class OPTForCausalLM(nn.Module, SupportsPP):
324
super().__init__()
325
config = vllm_config.model_config.hf_config
326
quant_config = vllm_config.quant_config
327
- super().__init__()
327
self.config = config
328
self.quant_config = quant_config
329
self.model = OPTModel(vllm_config=vllm_config,