mirror of
https://github.com/wassname/vllm.git
synced 2026-08-16 11:30:44 +08:00
[platform] add device_control env var (#12009)
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
@@ -78,20 +78,30 @@ class Platform:
|
||||
_enum: PlatformEnum
|
||||
device_name: str
|
||||
device_type: str
|
||||
|
||||
# available dispatch keys:
|
||||
# check https://github.com/pytorch/pytorch/blob/313dac6c1ca0fa0cde32477509cce32089f8532a/torchgen/model.py#L134 # noqa
|
||||
# use "CPU" as a fallback for platforms not registered in PyTorch
|
||||
dispatch_key: str = "CPU"
|
||||
|
||||
# available ray device keys:
|
||||
# https://github.com/ray-project/ray/blob/10ba5adadcc49c60af2c358a33bb943fb491a171/python/ray/_private/ray_constants.py#L438 # noqa
|
||||
# empty string means the device does not support ray
|
||||
ray_device_key: str = ""
|
||||
|
||||
# platform-agnostic way to specify the device control environment variable,
|
||||
# .e.g. CUDA_VISIBLE_DEVICES for CUDA.
|
||||
# hint: search for "get_visible_accelerator_ids_env_var" in
|
||||
# https://github.com/ray-project/ray/tree/master/python/ray/_private/accelerators # noqa
|
||||
device_control_env_var: str = "VLLM_DEVICE_CONTROL_ENV_VAR_PLACEHOLDER"
|
||||
|
||||
# The torch.compile backend for compiling simple and
|
||||
# standalone functions. The default value is "inductor" to keep
|
||||
# the same behavior as PyTorch.
|
||||
# NOTE: for the forward part of the model, vLLM has another separate
|
||||
# compilation strategy.
|
||||
simple_compile_backend: str = "inductor"
|
||||
|
||||
supported_quantization: list[str] = []
|
||||
|
||||
def is_cuda(self) -> bool:
|
||||
|
||||
Reference in New Issue
Block a user