Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Co-authored-by: kourosh hakhamaneshi <kouroshHakha@users.noreply.github.com>
This commit is contained in:
co-authored by
Claude
Codex
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
kourosh hakhamaneshi
parent
e9de72fe6c
commit
ebfbcfe46a
@@ -93,7 +93,7 @@ try:
|
||||
def get_node_ip(self) -> str:
|
||||
return get_ip()
|
||||
|
||||
def get_node_and_gpu_ids(self) -> tuple[str, list[int]]:
|
||||
def get_node_and_physical_gpu_ids(self) -> tuple[str, list[int]]:
|
||||
node_id = ray.get_runtime_context().get_node_id()
|
||||
device_key = vllm.platforms.current_platform.ray_device_key
|
||||
if not device_key:
|
||||
@@ -101,8 +101,10 @@ try:
|
||||
"current platform %s does not support ray.",
|
||||
vllm.platforms.current_platform.device_name,
|
||||
)
|
||||
gpu_ids = ray.get_runtime_context().get_accelerator_ids()[device_key]
|
||||
return node_id, gpu_ids
|
||||
physical_gpu_ids = ray.get_runtime_context().get_accelerator_ids()[
|
||||
device_key
|
||||
]
|
||||
return node_id, physical_gpu_ids
|
||||
|
||||
def setup_device_if_necessary(self):
|
||||
# TODO(swang): This is needed right now because Ray CG executes
|
||||
|
||||
Reference in New Issue
Block a user