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:
Tyler Michael Smith
2026-06-20 13:38:10 -07:00
committed by GitHub
co-authored by Claude Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> kourosh hakhamaneshi
parent e9de72fe6c
commit ebfbcfe46a
24 changed files with 722 additions and 185 deletions
@@ -364,7 +364,7 @@ class MockVLLMServer:
await self._serve_task
def launch_mock_vllm(child_args: argparse.Namespace, env_updates: dict[str, str]):
def launch_mock_vllm(child_args: argparse.Namespace):
logger.info("Launching mock vLLM on port %s", child_args.port)
mock_vllm = MockVLLMServer(
port=child_args.port,
@@ -375,7 +375,7 @@ def launch_mock_vllm(child_args: argparse.Namespace, env_updates: dict[str, str]
def launch_mock_vllm_with_drain(
child_args: argparse.Namespace, env_updates: dict[str, str]
child_args: argparse.Namespace,
):
logger.info("Launching mock vLLM with 15s drain on port %s", child_args.port)
mock_vllm = MockVLLMServer(