EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[VLM] Adopt fast image processor by default (#5065)

Browse Source
This commit is contained in:
Mick
2025-04-12 12:46:58 +08:00
committed by GitHub
parent 611720919d
commit 34ef6c8135
12 changed files with 163 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/backend/server_arguments.md
View File

@@ -45,7 +45,7 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
Please consult the documentation below to learn more about the parameters you may provide when launching a server.
## Model and tokenizer
## Model, processor and tokenizer
* `model_path`: Path to the model that will be served.
* `tokenizer_path`: Defaults to the `model_path`.
@@ -62,6 +62,7 @@ Please consult the documentation below to learn more about the parameters you ma
* `skip_tokenizer_init`: Set to true to provide the tokens to the engine and get the output tokens directly, typically used in RLHF. Please see this [example for reference](https://github.com/sgl-project/sglang/blob/main/examples/runtime/token_in_token_out/).
* `json_model_override_args`: Override model config with the provided JSON.
* `delete_ckpt_after_loading`: Delete the model checkpoint after loading the model.
* `disable_fast_image_processor`: Adopt base image processor instead of fast image processor(which is by default). For more detail, see: https://huggingface.co/docs/transformers/main/en/main_classes/image_processor#image-processor
## Serving: HTTP & API