[Bugfix] Proper input validation for multi-modal encoder-decoder models (#16156)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-09 00:45:21 +08:00
parent dc96fd54c6
commit 4ebc0b9640
10 changed files with 113 additions and 62 deletions
--- a/examples/offline_inference/encoder_decoder_multimodal.py
+++ b/examples/offline_inference/encoder_decoder_multimodal.py
@@ -56,7 +56,7 @@ def run_florence2():
 def run_mllama():
    engine_args = EngineArgs(
        model="meta-llama/Llama-3.2-11B-Vision-Instruct",
-        max_model_len=4096,
+        max_model_len=8192,
        max_num_seqs=2,
        limit_mm_per_prompt={"image": 1},
        dtype="half",