@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 0d0e3a42ac
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, 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()