Usage for vllm_generic.py

modal-labs · Jan 12, 2024 · ffa5c43 · ffa5c43
1 parent 72533c3
commit ffa5c43
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/06_gpu_and_ml/vllm_generic.py b/06_gpu_and_ml/vllm_generic.py
@@ -1,7 +1,7 @@
 # # Generic model inference with vLLM
+# Usage: modal deploy vllm_generic.py --public
 
 
-import os
 import time
 
 from modal import Image, Stub, method, Secret

diff --git a/06_gpu_and_ml/vllm_generic_client.py b/06_gpu_and_ml/vllm_generic_client.py
@@ -1,6 +1,9 @@
+# Usage:
+# 1. `modal volume create my-hf-cache`
+# 2. `python vllm_generic.py`
+
 import modal
 
-# First run `modal volume create my-hf-cache` in CLI first.
 model_vol = modal.Volume.lookup("my-hf-cache")
 hf_secret = modal.Secret.lookup("huggingface")