[Quantization][V1] BitsAndBytes support V1 (#15611)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-28 10:12:47 +08:00
parent bd45912b99
commit 726efc6a32
7 changed files with 52 additions and 24 deletions
--- a/tests/models/test_transformers.py
+++ b/tests/models/test_transformers.py
@@ -72,7 +72,6 @@ def test_distributed(
        "meta-llama/Llama-3.2-1B-Instruct",
        {
            "quantization": "bitsandbytes",
-            "load_format": "bitsandbytes",
        },
    ),
 ])