Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ROCm][AMD][Bugfix] unify CUDA_VISIBLE_DEVICES usage in vllm to get device count and fixed navi3x #6352

Merged
merged 2 commits into from
Jul 12, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
ruff: remove unused imports
  • Loading branch information
hongxiayang committed Jul 11, 2024
commit 42e4387037e4f4b1e897752cd724a64b1200d37c
2 changes: 1 addition & 1 deletion tests/distributed/test_utils.py
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
import ray

import vllm.envs as envs
from vllm.utils import (cuda_device_count_stateless, is_hip,
from vllm.utils import (cuda_device_count_stateless,
update_environment_variables)


3 changes: 1 addition & 2 deletions vllm/config.py
Original file line number Diff line number Diff line change
@@ -6,15 +6,14 @@
import torch
from transformers import PretrainedConfig

import vllm.envs as envs
from vllm.logger import init_logger
from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
from vllm.model_executor.models import ModelRegistry
from vllm.tracing import is_otel_installed
from vllm.transformers_utils.config import get_config, get_hf_text_config
from vllm.utils import (cuda_device_count_stateless, get_cpu_memory, is_cpu,
is_hip, is_neuron, is_openvino, is_tpu, is_xpu,
print_warning_once, update_environment_variables)
print_warning_once)

if TYPE_CHECKING:
from ray.util.placement_group import PlacementGroup
2 changes: 1 addition & 1 deletion vllm/worker/worker_base.py
Original file line number Diff line number Diff line change
@@ -11,7 +11,7 @@
from vllm.lora.request import LoRARequest
from vllm.sequence import (ExecuteModelRequest, IntermediateTensors,
SamplerOutput)
from vllm.utils import (enable_trace_function_call_for_thread, is_hip,
from vllm.utils import (enable_trace_function_call_for_thread,
update_environment_variables)
from vllm.worker.model_runner_base import ModelRunnerBase, ModelRunnerInputBase

Loading