[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/encoder_decoder/vision_language/test_mllama.py
+++ b/tests/models/encoder_decoder/vision_language/test_mllama.py
@@ -425,7 +425,6 @@ def test_bnb_regression(
        max_model_len=4096,
        max_num_seqs=2,
        quantization="bitsandbytes",
-        load_format="bitsandbytes",
    )
    sampling_params = SamplingParams(
        temperature=0,