diff --git a/06_gpu_and_ml/vllm_inference.py b/06_gpu_and_ml/vllm_inference.py index 1138c3793..3e216f53c 100644 --- a/06_gpu_and_ml/vllm_inference.py +++ b/06_gpu_and_ml/vllm_inference.py @@ -68,7 +68,7 @@ def download_model_to_folder(): "hf-transfer==0.1.4", "torch==2.1.2", "torchvision==0.16.2", - "torchaudio==2.1.2" + "torchaudio==2.1.2", ) # Use the barebones hf-transfer package for maximum download speeds. No progress bar, but expect 700MB/s. .env({"HF_HUB_ENABLE_HF_TRANSFER": "1"}) diff --git a/06_gpu_and_ml/vllm_mixtral.py b/06_gpu_and_ml/vllm_mixtral.py index 3fef9b5a5..aa128a01f 100644 --- a/06_gpu_and_ml/vllm_mixtral.py +++ b/06_gpu_and_ml/vllm_mixtral.py @@ -66,7 +66,7 @@ def download_model_to_folder(): "hf-transfer==0.1.4", "torch==2.1.2", "torchvision==0.16.2", - "torchaudio==2.1.2" + "torchaudio==2.1.2", ) .env({"HF_HUB_ENABLE_HF_TRANSFER": "1"}) .run_function(download_model_to_folder, timeout=60 * 20)