Remove openvino support in favor of external plugin (vllm-project#15339)

Signed-off-by: Russell Bryant <rbryant@redhat.com>

Author: russellb

.buildkite/run-openvino-test.sh

@@ -26,4 +26,3 @@ installation/ai_accelerator
   - Google TPU
   - Intel Gaudi
   - AWS Neuron
-  - OpenVINO

Dockerfile.openvino

@@ -36,16 +36,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "# Installation"
-:end-before: "## Requirements"
-:::
-
-::::
-
 :::::
 
 ## Requirements
@@ -83,16 +73,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "## Requirements"
-:end-before: "## Set up using Python"
-:::
-
-::::
-
 :::::
 
 ## Configure a new environment
@@ -130,14 +110,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} python_env_setup.inc.md
-:::
-
-::::
-
 :::::
 
 ## Set up using Python
@@ -177,16 +149,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "### Pre-built wheels"
-:end-before: "### Build wheel from source"
-:::
-
-::::
-
 :::::
 
 ### Build wheel from source
@@ -224,16 +186,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "### Build wheel from source"
-:end-before: "## Set up using Docker"
-:::
-
-::::
-
 :::::
 
 ## Set up using Docker
@@ -273,16 +225,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "### Pre-built images"
-:end-before: "### Build image from source"
-:::
-
-::::
-
 :::::
 
 ### Build image from source
@@ -320,16 +262,6 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "### Build image from source"
-:end-before: "## Extra information"
-:::
-
-::::
-
 :::::
 
 ## Extra information
@@ -364,13 +296,4 @@ vLLM is a Python library that supports the following AI accelerators. Select you
 
 ::::
 
-::::{tab-item} OpenVINO
-:sync: openvino
-
-:::{include} ai_accelerator/openvino.inc.md
-:start-after: "## Extra information"
-:::
-
-::::
-
 :::::

docs/source/getting_started/installation.md

@@ -449,10 +449,6 @@ def _is_cpu() -> bool:
     return VLLM_TARGET_DEVICE == "cpu"
 
 
-def _is_openvino() -> bool:
-    return VLLM_TARGET_DEVICE == "openvino"
-
-
 def _is_xpu() -> bool:
     return VLLM_TARGET_DEVICE == "xpu"
 
@@ -572,8 +568,6 @@ def get_vllm_version() -> str:
         if gaudi_sw_version != MAIN_CUDA_VERSION:
             gaudi_sw_version = gaudi_sw_version.replace(".", "")[:3]
             version += f"{sep}gaudi{gaudi_sw_version}"
-    elif _is_openvino():
-        version += f"{sep}openvino"
     elif _is_tpu():
         version += f"{sep}tpu"
     elif _is_cpu():
@@ -623,8 +617,6 @@ def _read_requirements(filename: str) -> list[str]:
         requirements = _read_requirements("neuron.txt")
     elif _is_hpu():
         requirements = _read_requirements("hpu.txt")
-    elif _is_openvino():
-        requirements = _read_requirements("openvino.txt")
     elif _is_tpu():
         requirements = _read_requirements("tpu.txt")
     elif _is_cpu():
@@ -634,7 +626,7 @@ def _read_requirements(filename: str) -> list[str]:
     else:
         raise ValueError(
             "Unsupported platform, please use CUDA, ROCm, Neuron, HPU, "
-            "OpenVINO, or CPU.")
+            "or CPU.")
     return requirements
 
 

docs/source/getting_started/installation/ai_accelerator.md

@@ -273,8 +273,7 @@ class HfRunner:
     def get_default_device(self):
         from vllm.platforms import current_platform
 
-        return ("cpu" if current_platform.is_cpu()
-                or current_platform.is_openvino() else "cuda")
+        return ("cpu" if current_platform.is_cpu() else "cuda")
 
     def wrap_device(self, x: _T, device: Optional[str] = None) -> _T:
         if x is None or isinstance(x, (bool, )):

docs/source/getting_started/installation/ai_accelerator/openvino.inc.md

@@ -1,14 +1,13 @@
 # SPDX-License-Identifier: Apache-2.0
 
-from unittest.mock import Mock, patch
+from unittest.mock import patch
 
 import pytest
 import torch
 
 from vllm.attention.selector import _cached_get_attn_backend, get_attn_backend
 from vllm.platforms.cpu import CpuPlatform
 from vllm.platforms.cuda import CudaPlatform
-from vllm.platforms.openvino import OpenVinoPlatform
 from vllm.platforms.rocm import RocmPlatform
 from vllm.utils import STR_BACKEND_ENV_VAR, STR_FLASH_ATTN_VAL, STR_INVALID_VAL
 
@@ -21,9 +20,9 @@ def clear_cache():
 
 
 @pytest.mark.parametrize(
-    "name", ["TORCH_SDPA", "ROCM_FLASH", "XFORMERS", "FLASHINFER", "OPENVINO"])
+    "name", ["TORCH_SDPA", "ROCM_FLASH", "XFORMERS", "FLASHINFER"])
 @pytest.mark.parametrize("use_v1", [True, False])
-@pytest.mark.parametrize("device", ["cpu", "openvino", "hip", "cuda"])
+@pytest.mark.parametrize("device", ["cpu", "hip", "cuda"])
 def test_env(
     name: str,
     use_v1: bool,
@@ -51,13 +50,6 @@ def test_env(
                                            16, False)
             EXPECTED = "TRITON_ATTN_VLLM_V1" if use_v1 else "ROCM_FLASH"
             assert backend.get_name() == EXPECTED
-        elif device == "openvino":
-            with patch("vllm.attention.selector.current_platform",
-                       OpenVinoPlatform()), patch.dict('sys.modules',
-                                                       {'openvino': Mock()}):
-                backend = get_attn_backend(16, torch.float16, torch.float16,
-                                           16, False)
-            assert backend.get_name() == "OPENVINO"
         else:
             if name in ["XFORMERS", "FLASHINFER"]:
                 with patch("vllm.attention.selector.current_platform",