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, 23:15 UTC
[Bugfix][Hardware][Intel CPU] Fix unpassed multi_modal_kwargs for CPU runner (#5956)
Isotr0py committed
Jun 28, 2024 at 20:03 UTC
0d0e3a42ac80eb41fc50f139fe31fde8e0b5bf8e
1 file changed
+1
vllm/worker/cpu_model_runner.py
+1
@@ -355,6 +355,7 @@ class CPUModelRunner(ModelRunnerBase[CPUModelInput]):
355
input_positions=input_positions,
356
attn_metadata=attn_metadata,
357
sampling_metadata=sampling_metadata,
358
+ multi_modal_kwargs=multi_modal_kwargs,
359
)
360
361
@torch.inference_mode()