A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 13, 09:30 UTC
[CI/Build] Fix crash due to removed VLLM_USE_V1 attribute in EPD (#28521)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com> Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com> Co-authored-by: Roger Wang <hey@rogerw.io>
Chenguang Zheng committed
Nov 12, 2025 at 15:09 UTC
91864b79b36e5a7799f90c1c350e663d484bcfee
1 file changed
+3
-7
vllm/distributed/ec_transfer/ec_transfer_state.py
+3
-7
@@ -2,7 +2,6 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
from typing import TYPE_CHECKING
4
5
-from vllm import envs
5
from vllm.distributed.ec_transfer.ec_connector.base import (
6
ECConnectorBase,
7
ECConnectorRole,
@@ -38,9 +37,6 @@ def ensure_ec_transfer_initialized(vllm_config: "VllmConfig") -> None:
37
vllm_config.ec_transfer_config.is_ec_transfer_instance
38
and _EC_CONNECTOR_AGENT is None
39
):
41
- if envs.VLLM_USE_V1:
42
- _EC_CONNECTOR_AGENT = ECConnectorFactory.create_connector(
43
- config=vllm_config, role=ECConnectorRole.WORKER
44
- )
45
- else:
46
- raise ValueError("V0 is no longer supported")
40
+ _EC_CONNECTOR_AGENT = ECConnectorFactory.create_connector(
41
+ config=vllm_config, role=ECConnectorRole.WORKER
42
+ )