add info for clarity

vllm-project · Dec 21, 2024 · d31b31b · d31b31b
1 parent 9d49435
commit d31b31b
Showing 1 changed file with 4 additions and 2 deletions.
diff --git a/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py b/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py
@@ -54,6 +54,8 @@
     warmup_ratio=warmup_ratio,
 )
 logger.info(
-    "Note: vLLM requires the dtype=torch.float16 when running the ",
-    "compressed marlin-24 model",
+    "Note: llcompressor does not currently support running ",
+    "compressed models in the marlin-24 format. The model ",
+    "produced from this example can be run on vLLM with ",
+    "dtype=torch.float16",
 )