@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 0ce7798f44
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 16, 09:30 UTC

[Misc]: Typo fix: Renaming classes (casualLM -> causalLM) (#9801)

Signed-off-by: Yannick Schnider <Yannick.Schnider1@ibm.com>

yannicks1 committed Oct 29, 2024 at 18:39 UTC 0ce7798f44c586e11c65d59725724eb805086e93
2 files changed +4 -4
vllm/model_executor/model_loader/neuron.py
+2 -2
@@ -37,7 +37,7 @@ _NEURON_SUPPORTED_MODELS: Dict[str, Tuple[str, str, str]] = {
37 }
38
39
40 -class NeuronCasualLM(nn.Module):
40 +class NeuronCausalLM(nn.Module):
41
42 def __init__(self,
43 config: PretrainedConfig,
@@ -184,7 +184,7 @@ def get_neuron_model(model_config: ModelConfig,
184 scheduler_config: SchedulerConfig) -> nn.Module:
185
186 # Create a model instance.
187 - model = NeuronCasualLM(
187 + model = NeuronCausalLM(
188 model_config.hf_config,
189 _is_neuron_on_device_sampling_disabled(model_config))
190
vllm/model_executor/model_loader/openvino.py
+2 -2
@@ -95,7 +95,7 @@ def _require_model_export(model_id, revision=None, subfolder=None):
95 return True
96
97
98 -class OpenVINOCasualLM(nn.Module):
98 +class OpenVINOCausalLM(nn.Module):
99
100 def __init__(
101 self,
@@ -199,5 +199,5 @@ def get_model(
199 "be added in the future. If this is important to you, "
200 "please open an issue on github.")
201
202 - return OpenVINOCasualLM(ov_core, model_config, device_config,
202 + return OpenVINOCausalLM(ov_core, model_config, device_config,
203 kv_cache_dtype)