[P/D]Make kv-transfer env variable take effect & Fix load-balance proxy (#3981)

### What this PR does / why we need it?
Make kv-transfer env variable take effect and Fix load-balance proxy.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
By CI.


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: liziyu <liziyu16@huawei.com>
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
This commit is contained in:
zxr2333
2025-11-06 12:02:47 +08:00
committed by GitHub
parent 737cad2b6b
commit b206e831e9
7 changed files with 33 additions and 13 deletions

View File

@@ -31,6 +31,7 @@ from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.request import Request, RequestStatus
import vllm_ascend.envs as envs_ascend
from vllm_ascend.distributed.utils import get_transfer_timeout_value
from vllm_ascend.utils import (AscendSocVersion, get_ascend_soc_version,
prefill_context_parallel_enable,
vllm_version_is)
@@ -438,7 +439,7 @@ class LLMDataDistCMgrConnectorWorker():
assert self.local_agent_metadata is not None
llm_config = LLMConfig()
llm_config.device_id = self.local_rank
llm_config.sync_kv_timeout = 20000
llm_config.sync_kv_timeout = get_transfer_timeout_value()
llm_config.enable_switch_role = True
llm_config.enable_cache_manager = True
llm_config.enable_remote_cache_accessible = True