From 131ae3d294e015f918fc5d63590878053b1de298 Mon Sep 17 00:00:00 2001 From: ByeongkiJeong Date: Tue, 4 Jun 2024 09:55:52 +0900 Subject: [PATCH] Update inference_on_multiple_gpus.md typos --- docs/inference_on_multiple_gpus.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/inference_on_multiple_gpus.md b/docs/inference_on_multiple_gpus.md index f820070..ced985f 100644 --- a/docs/inference_on_multiple_gpus.md +++ b/docs/inference_on_multiple_gpus.md @@ -43,7 +43,7 @@ gpu_device_ids = [0, 1] # Define which gpu to use (now we have two GPUs, each ha no_split_module_classes = ["LlamaDecoderLayer"] max_memory = { - device_id: memory for device_id in gpu_device_ids + device_id: max_memory_each_gpu for device_id in gpu_device_ids } config = AutoConfig.from_pretrained(