[vlm] Remove vision language config. (#6089)

Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
xwjiang2010
2024-07-03 15:14:16 -07:00
committed by GitHub
parent 3c6325f0fc
commit d9e98f42e4
43 changed files with 371 additions and 465 deletions

View File

@@ -14,15 +14,13 @@ def run_phi3v():
# Note: The default setting of max_num_seqs (256) and
# max_model_len (128k) for this model may cause OOM.
# You may lower either to run this example on lower-end GPUs.
# In this example, we override max_num_seqs to 5 while
# keeping the original context length of 128k.
llm = LLM(
model=model_path,
trust_remote_code=True,
image_token_id=32044,
image_input_shape="1,3,1008,1344",
# Use the maximum possible value for memory profiling
image_feature_size=2653,
max_num_seqs=5,
)