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
@@ -302,6 +302,14 @@ class ParallelConfig:
|
||||
Each entry must use `numactl --physcpubind` CPU-list syntax, for example
|
||||
`"0-3"` or `"0,2,4-7"`.
|
||||
"""
|
||||
assigned_physical_gpu_ids: list[int] | None = None
|
||||
"""Mapping from vLLM-local logical GPU IDs to physical GPU IDs.
|
||||
|
||||
For example, ``[2, 3]`` means logical GPU 0 maps to physical GPU 2,
|
||||
and logical GPU 1 maps to physical GPU 3. Physical IDs are used only
|
||||
at platform/topology boundaries such as NVML, NIC affinity, P2P
|
||||
checks, and final CUDA device selection when needed. When None,
|
||||
logical IDs map to visible device IDs in order."""
|
||||
|
||||
distributed_timeout_seconds: int | None = None
|
||||
"""Timeout in seconds for distributed operations (e.g., init_process_group).
|
||||
@@ -772,6 +780,7 @@ class ParallelConfig:
|
||||
"numa_bind",
|
||||
"numa_bind_nodes",
|
||||
"numa_bind_cpus",
|
||||
"assigned_physical_gpu_ids",
|
||||
}
|
||||
|
||||
from vllm.config.utils import get_hash_factors, hash_factors
|
||||
|
||||
Reference in New Issue
Block a user