vllm/vllm/transformers_utils
Cyrus Leung 9831aec49f
[Core] Dynamic image size support for VLMs (#5276)
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-07-02 20:34:00 -07:00
..
configs [Model] Changes to MLPSpeculator to support tie_weights and input_scale (#5965) 2024-07-01 16:40:02 -07:00
tokenizer_group [Bugfix] Use RayActorError for older versions of Ray in RayTokenizerGroupPool (#6039) 2024-07-01 20:12:40 +00:00
tokenizers [Mypy] Part 3 fix typing for nested directories for most of directory (#4161) 2024-04-22 21:32:44 -07:00
__init__.py [Tokenizer] Add an option to specify tokenizer (#284) 2023-06-28 09:46:58 -07:00
config.py [Bugfix] Support eos_token_id from config.json (#5954) 2024-06-29 11:19:02 +00:00
detokenizer.py [mypy] Enable type checking for test directory (#5017) 2024-06-15 04:45:31 +00:00
image_processor.py [Core] Dynamic image size support for VLMs (#5276) 2024-07-02 20:34:00 -07:00
tokenizer.py [Misc] centralize all usage of environment variables (#4548) 2024-05-02 11:13:25 -07:00