xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-17 12:02:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source 
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
This commit is contained in:
inkcherry 2025-11-24 09:18:49 +00:00
parent 7d3a93f1e7
commit b3b195a540
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/distributed/kv_transfer/kv_connector/v1/moriio_connector.py
View File

@ -20,7 +20,6 @@ import numpy as np
import torch import torch
import zmq import zmq
from vllm import envs
from vllm.attention.backends.registry import AttentionBackendEnum from vllm.attention.backends.registry import AttentionBackendEnum
from vllm.attention.selector import get_attn_backend from vllm.attention.selector import get_attn_backend
from vllm.config import VllmConfig from vllm.config import VllmConfig
@ -1014,9 +1013,8 @@ class MoRIIOConnectorScheduler:
self.vllm_config = vllm_config self.vllm_config = vllm_config
self.block_size = vllm_config.cache_config.block_size self.block_size = vllm_config.cache_config.block_size
self.engine_id: EngineId = engine_id self.engine_id: EngineId = engine_id
self.side_channel_host = envs.VLLM_NIXL_SIDE_CHANNEL_HOST
self.mode = get_moriio_mode() self.mode = get_moriio_mode()
self.host_ip = get_ip()
self.handshake_port = ( self.handshake_port = (
self.vllm_config.kv_transfer_config.kv_connector_extra_config[ self.vllm_config.kv_transfer_config.kv_connector_extra_config[
"handshake_port" "handshake_port"
@ -1305,7 +1303,7 @@ class MoRIIOConnectorScheduler:
do_remote_decode=False, do_remote_decode=False,
remote_block_ids=computed_block_ids, remote_block_ids=computed_block_ids,
remote_engine_id=self.engine_id, remote_engine_id=self.engine_id,
remote_host=self.side_channel_host, remote_host=self.host_ip,
remote_port=self.handshake_port, remote_port=self.handshake_port,
tp_size=self.vllm_config.parallel_config.tensor_parallel_size, tp_size=self.vllm_config.parallel_config.tensor_parallel_size,
) )