[vlm] Remove vision language config.

docs/source/models/vlm.rst

@@ -33,12 +33,7 @@ To initialize a VLM, the aforementioned arguments must be passed to the ``LLM``
 
 .. code-block:: python
 
-    llm = LLM(
-        model="llava-hf/llava-1.5-7b-hf",
-        image_token_id=32000,
-        image_input_shape="1,3,336,336",
-        image_feature_size=576,
-    )
+    llm = LLM(model="llava-hf/llava-1.5-7b-hf")
 
 .. important::
     Currently, you have to specify ``image_feature_size`` to support memory profiling.

examples/llava_example.py

@@ -10,12 +10,7 @@
 
 
 def run_llava():
-    llm = LLM(
-        model="llava-hf/llava-1.5-7b-hf",
-        image_token_id=32000,
-        image_input_shape="1,3,336,336",
-        image_feature_size=576,
-    )
+    llm = LLM(model="llava-hf/llava-1.5-7b-hf")
 
     prompt = "USER: <image>\nWhat is the content of this image?\nASSISTANT:"
 

examples/llava_next_example.py

@@ -7,13 +7,7 @@
 
 
 def run_llava_next():
-    llm = LLM(
-        model="llava-hf/llava-v1.6-mistral-7b-hf",
-        image_token_id=32000,
-        image_input_shape="1,3,336,336",
-        # Use the maximum possible value for memory profiling
-        image_feature_size=2928,
-    )
+    llm = LLM(model="llava-hf/llava-v1.6-mistral-7b-hf")
 
     prompt = "[INST] <image>\nWhat is shown in this image? [/INST]"
     url = "https://h2o-release.s3.amazonaws.com/h2ogpt/bigben.jpg"

examples/openai_vision_api_client.py

@@ -3,9 +3,6 @@
 Launch the vLLM server with the following command:
 python -m vllm.entrypoints.openai.api_server \
     --model llava-hf/llava-1.5-7b-hf \
-    --image-token-id 32000 \
-    --image-input-shape 1,3,336,336 \
-    --image-feature-size 576 \
     --chat-template template_llava.jinja
 """
 import base64

examples/phi3v_example.py

@@ -19,11 +19,7 @@ def run_phi3v():
     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,
+        max_num_seqs=1,
     )
 
     image = Image.open("images/cherry_blossom.jpg")

tests/distributed/test_multimodal_broadcast.py

@@ -20,9 +20,9 @@
 model = os.environ["TEST_DIST_MODEL"]
 
 if model.startswith("llava-hf/llava"):
-    from ..models.test_llava import model_and_vl_config, run_test
+    from ..models.test_llava import models, run_test
 elif model.startswith("microsoft/Phi-3-vision"):
-    from ..models.test_phi3v import model_and_vl_config, run_test
+    from ..models.test_phi3v import models, run_test
 else:
     raise NotImplementedError(f"Unsupported model: {model}")
 
@@ -44,7 +44,7 @@ def test_models(hf_runner, vllm_runner, image_assets,
         hf_runner,
         vllm_runner,
         image_assets,
-        model_and_config=model_and_vl_config[0],
+        model=models[0],
         size_factors=[1.0],
         dtype=dtype,
         max_tokens=max_tokens,

tests/models/test_llava.py

@@ -3,7 +3,6 @@
 import pytest
 from transformers import AutoTokenizer
 
-from vllm.config import VisionLanguageConfig
 from vllm.multimodal.utils import rescale_image_size
 from vllm.sequence import SampleLogprobs
 
@@ -21,49 +20,27 @@
     "USER: <image>\nWhat's in this image?\nASSISTANT:",
 })
 
+IMAGE_TOKEN_ID = 32000
 
-def iter_llava_configs(model_name: str):
-    image_hw_to_feature_size = {
-        (336, 336): 576,
-    }
-
-    for (h, w), f in image_hw_to_feature_size.items():
-        input_shape = (1, 3, h, w)
-        yield (model_name,
-               VisionLanguageConfig(image_feature_size=f,
-                                    image_token_id=32000,
-                                    image_input_shape=input_shape))
-
-
-model_and_vl_config = [
-    *iter_llava_configs("llava-hf/llava-1.5-7b-hf"),
-]
+models = ["llava-hf/llava-1.5-7b-hf"]
 
 
 def vllm_to_hf_output(vllm_output: Tuple[List[int], str,
                                          Optional[SampleLogprobs]],
-                      vlm_config: VisionLanguageConfig, model_id: str):
-    """Sanitize vllm output to be comparable with hf output.
-    The function reduces `input_ids` from 1, 32000, 32000, ..., 32000,
-    x1, x2, x3 ... to 1, 32000, x1, x2, x3 ...
-    It also reduces `output_str` from "<image><image>bla" to "bla".
-    """
+                      model: str):
+    """Sanitize vllm output to be comparable with hf output."""
     output_ids, output_str, out_logprobs = vllm_output
-    image_token_id = vlm_config.image_token_id
 
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    image_token_str = tokenizer.decode(image_token_id)
+    tokenizer = AutoTokenizer.from_pretrained(model)
     eos_token_id = tokenizer.eos_token_id
 
     hf_output_ids = [
         token_id for idx, token_id in enumerate(output_ids)
-        if token_id != image_token_id or output_ids[idx - 1] != image_token_id
+        if token_id != IMAGE_TOKEN_ID or output_ids[idx - 1] != IMAGE_TOKEN_ID
     ]
 
-    hf_output_str = output_str \
-        .replace(image_token_str * vlm_config.image_feature_size, "")
-    assert hf_output_str[0] == " "
-    hf_output_str = hf_output_str[1:]
+    assert output_str[0] == " "
+    hf_output_str = output_str[1:]
     if hf_output_ids[-1] == eos_token_id:
         hf_output_str = hf_output_str + tokenizer.decode(eos_token_id)
 
@@ -74,7 +51,7 @@ def run_test(
     hf_runner: Type[HfRunner],
     vllm_runner: Type[VllmRunner],
     image_assets: _ImageAssets,
-    model_and_config: Tuple[str, VisionLanguageConfig],
+    model,
     *,
     size_factors: List[float],
     dtype: str,
@@ -92,7 +69,6 @@ def run_test(
     Note, the text input is also adjusted to abide by vllm contract.
     The text output is sanitized to be able to compare with hf.
     """
-    model_id, vlm_config = model_and_config
     images = [asset.pil_image for asset in image_assets]
 
     inputs_per_image = [(
@@ -106,12 +82,11 @@ def run_test(
     # will hurt multiprocessing backend with fork method (the default method).
 
     # max_model_len should be greater than image_feature_size
-    with vllm_runner(model_id,
+    with vllm_runner(model,
                      dtype=dtype,
                      tensor_parallel_size=tensor_parallel_size,
                      distributed_executor_backend=distributed_executor_backend,
-                     enforce_eager=True,
-                     **vlm_config.as_cli_args_dict()) as vllm_model:
+                     enforce_eager=True) as vllm_model:
         vllm_outputs_per_image = [
             vllm_model.generate_greedy_logprobs(prompts,
                                                 max_tokens,
@@ -120,7 +95,7 @@ def run_test(
             for prompts, images in inputs_per_image
         ]
 
-    with hf_runner(model_id, dtype=dtype, is_vision_model=True) as hf_model:
+    with hf_runner(model, dtype=dtype, is_vision_model=True) as hf_model:
         hf_outputs_per_image = [
             hf_model.generate_greedy_logprobs_limit(prompts,
                                                     max_tokens,
@@ -136,15 +111,15 @@ def run_test(
         check_logprobs_close(
             outputs_0_lst=hf_outputs,
             outputs_1_lst=[
-                vllm_to_hf_output(vllm_output, vlm_config, model_id)
+                vllm_to_hf_output(vllm_output, model)
                 for vllm_output in vllm_outputs
             ],
             name_0="hf",
             name_1="vllm",
         )
 
 
-@pytest.mark.parametrize("model_and_config", model_and_vl_config)
+@pytest.mark.parametrize("model", models)
 @pytest.mark.parametrize(
     "size_factors",
     [
@@ -161,14 +136,13 @@ def run_test(
 @pytest.mark.parametrize("dtype", ["half"])
 @pytest.mark.parametrize("max_tokens", [128])
 @pytest.mark.parametrize("num_logprobs", [5])
-def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
-                size_factors, dtype: str, max_tokens: int,
-                num_logprobs: int) -> None:
+def test_models(hf_runner, vllm_runner, image_assets, model, size_factors,
+                dtype: str, max_tokens: int, num_logprobs: int) -> None:
     run_test(
         hf_runner,
         vllm_runner,
         image_assets,
-        model_and_config,
+        model,
         size_factors=size_factors,
         dtype=dtype,
         max_tokens=max_tokens,

tests/models/test_llava_next.py

@@ -4,7 +4,6 @@
 import pytest
 from transformers import AutoTokenizer
 
-from vllm.config import VisionLanguageConfig
 from vllm.multimodal.utils import rescale_image_size
 from vllm.sequence import SampleLogprobs
 
@@ -27,46 +26,22 @@
     f"{_PREFACE} USER: <image>\nWhat's in this image? ASSISTANT:",
 })
 
-
-def iter_llava_next_configs(model_name: str):
-    # Need to use the max possible feature size for profile_run
-    image_hw_to_feature_size = {
-        (336, 336): 2928,
-    }
-
-    for (h, w), f in image_hw_to_feature_size.items():
-        input_shape = (1, 3, h, w)
-        yield (model_name,
-               VisionLanguageConfig(
-                   image_feature_size=f,
-                   image_token_id=32000,
-                   image_input_shape=input_shape,
-               ))
-
-
-model_and_vl_config = [
-    *iter_llava_next_configs("llava-hf/llava-v1.6-vicuna-7b-hf"),
-]
+IMAGE_TOKEN_ID = 32000
 
 
 def vllm_to_hf_output(vllm_output: Tuple[List[int], str,
                                          Optional[SampleLogprobs]],
-                      vlm_config: VisionLanguageConfig, model_id: str):
-    """Sanitize vllm output to be comparable with hf output.
-    The function reduces `input_ids` from 1, 32000, 32000, ..., 32000,
-    x1, x2, x3 ... to 1, 32000, x1, x2, x3 ...
-    It also reduces `output_str` from "<image><image>bla" to "bla".
-    """
+                      model: str):
+    """Sanitize vllm output to be comparable with hf output."""
     output_ids, output_str, out_logprobs = vllm_output
-    image_token_id = vlm_config.image_token_id
 
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    image_token_str = tokenizer.decode(image_token_id)
+    tokenizer = AutoTokenizer.from_pretrained(model)
+    image_token_str = tokenizer.decode(IMAGE_TOKEN_ID)
     eos_token_id = tokenizer.eos_token_id
 
     hf_output_ids = [
         token_id for idx, token_id in enumerate(output_ids)
-        if token_id != image_token_id or output_ids[idx - 1] != image_token_id
+        if token_id != IMAGE_TOKEN_ID or output_ids[idx - 1] != IMAGE_TOKEN_ID
     ]
 
     hf_output_str = re.sub(fr"({image_token_str})+", "", output_str)
@@ -78,7 +53,7 @@ def vllm_to_hf_output(vllm_output: Tuple[List[int], str,
     return hf_output_ids, hf_output_str, out_logprobs
 
 
-@pytest.mark.parametrize("model_and_config", model_and_vl_config)
+@pytest.mark.parametrize("model", ["llava-hf/llava-v1.6-vicuna-7b-hf"])
 @pytest.mark.parametrize(
     "size_factors",
     [
@@ -95,9 +70,8 @@ def vllm_to_hf_output(vllm_output: Tuple[List[int], str,
 @pytest.mark.parametrize("dtype", ["half"])
 @pytest.mark.parametrize("max_tokens", [128])
 @pytest.mark.parametrize("num_logprobs", [5])
-def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
-                size_factors, dtype: str, max_tokens: int,
-                num_logprobs: int) -> None:
+def test_models(hf_runner, vllm_runner, image_assets, model, size_factors,
+                dtype: str, max_tokens: int, num_logprobs: int) -> None:
     """Inference result should be the same between hf and vllm.
 
     All the image fixtures for the test is under tests/images.
@@ -107,7 +81,6 @@ def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
     Note, the text input is also adjusted to abide by vllm contract.
     The text output is sanitized to be able to compare with hf.
     """
-    model_id, vlm_config = model_and_config
     images = [asset.pil_image for asset in image_assets]
 
     inputs_per_image = [(
@@ -116,11 +89,10 @@ def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
     ) for image, prompt in zip(images, HF_IMAGE_PROMPTS)]
 
     # max_model_len should be greater than image_feature_size
-    with vllm_runner(model_id,
+    with vllm_runner(model,
                      dtype=dtype,
                      max_model_len=4096,
-                     enforce_eager=True,
-                     **vlm_config.as_cli_args_dict()) as vllm_model:
+                     enforce_eager=True) as vllm_model:
         vllm_outputs_per_image = [
             vllm_model.generate_greedy_logprobs(prompts,
                                                 max_tokens,
@@ -129,7 +101,7 @@ def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
             for prompts, images in inputs_per_image
         ]
 
-    with hf_runner(model_id, dtype=dtype, is_vision_model=True) as hf_model:
+    with hf_runner(model, dtype=dtype, is_vision_model=True) as hf_model:
         hf_outputs_per_image = [
             hf_model.generate_greedy_logprobs_limit(prompts,
                                                     max_tokens,
@@ -145,7 +117,7 @@ def test_models(hf_runner, vllm_runner, image_assets, model_and_config,
         check_logprobs_close(
             outputs_0_lst=hf_outputs,
             outputs_1_lst=[
-                vllm_to_hf_output(vllm_output, vlm_config, model_id)
+                vllm_to_hf_output(vllm_output, model)
                 for vllm_output in vllm_outputs
             ],
             name_0="hf",