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
@@ -286,6 +286,12 @@ class WorkerWrapperBase:
|
||||
extended_calls,
|
||||
)
|
||||
|
||||
assigned_physical_gpu_ids = kwargs.pop("assigned_physical_gpu_ids", None)
|
||||
if assigned_physical_gpu_ids is not None:
|
||||
vllm_config.parallel_config.assigned_physical_gpu_ids = (
|
||||
assigned_physical_gpu_ids
|
||||
)
|
||||
|
||||
shared_worker_lock = kwargs.pop("shared_worker_lock", None)
|
||||
if shared_worker_lock is None:
|
||||
msg = (
|
||||
|
||||
Reference in New Issue
Block a user