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

Signed-off-by: Russell Bryant <rbryant@redhat.com>
This commit is contained in:
Russell Bryant
2025-03-22 14:06:39 -07:00
committed by GitHub
parent dd861b992f
commit b877031d80
20 changed files with 8 additions and 1789 deletions
+1 -27
View File
@@ -40,10 +40,6 @@ if TYPE_CHECKING:
VLLM_CPU_KVCACHE_SPACE: int = 0
VLLM_CPU_OMP_THREADS_BIND: str = ""
VLLM_CPU_MOE_PREPACK: bool = True
VLLM_OPENVINO_DEVICE: str = "CPU"
VLLM_OPENVINO_KVCACHE_SPACE: int = 0
VLLM_OPENVINO_CPU_KV_CACHE_PRECISION: Optional[str] = None
VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS: bool = False
VLLM_XLA_CACHE_PATH: str = os.path.join(VLLM_CACHE_ROOT, "xla_cache")
VLLM_XLA_CHECK_RECOMPILATION: bool = False
VLLM_FUSED_MOE_CHUNK_SIZE: int = 64 * 1024
@@ -131,7 +127,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# ================== Installation Time Env Vars ==================
# Target device of vLLM, supporting [cuda (by default),
# rocm, neuron, cpu, openvino]
# rocm, neuron, cpu]
"VLLM_TARGET_DEVICE":
lambda: os.getenv("VLLM_TARGET_DEVICE", "cuda"),
@@ -358,28 +354,6 @@ environment_variables: dict[str, Callable[[], Any]] = {
"VLLM_CPU_MOE_PREPACK":
lambda: bool(int(os.getenv("VLLM_CPU_MOE_PREPACK", "1"))),
# OpenVINO device selection
# default is CPU
"VLLM_OPENVINO_DEVICE":
lambda: os.getenv("VLLM_OPENVINO_DEVICE", "CPU").upper(),
# OpenVINO key-value cache space
# default is 4GB
"VLLM_OPENVINO_KVCACHE_SPACE":
lambda: int(os.getenv("VLLM_OPENVINO_KVCACHE_SPACE", "0")),
# OpenVINO KV cache precision
# default is bf16 if natively supported by platform, otherwise f16
# To enable KV cache compression, please, explicitly specify u8
"VLLM_OPENVINO_CPU_KV_CACHE_PRECISION":
lambda: os.getenv("VLLM_OPENVINO_CPU_KV_CACHE_PRECISION", None),
# Enables weights compression during model export via HF Optimum
# default is False
"VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS":
lambda:
(os.environ.get("VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS", "0").lower() in
("on", "true", "1")),
# If the env var is set, then all workers will execute as separate
# processes from the engine, and we use the same mechanism to trigger
# execution on all workers.