Remove VLLM_USE_V1 (#4086)
Drop VLLM_USE_V1 usage. This env has been removed from vLLM already.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
@@ -160,7 +160,6 @@ export TP_SOCKET_IFNAME=$nic_name
|
||||
export HCCL_SOCKET_IFNAME=$nic_name
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=100
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
|
||||
vllm serve vllm-ascend/DeepSeek-V3.1-W8A8 \
|
||||
|
||||
@@ -70,7 +70,6 @@ export TP_SOCKET_IFNAME=$nic_name
|
||||
export HCCL_SOCKET_IFNAME=$nic_name
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=100
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
|
||||
# The w8a8 weight can be obtained from https://www.modelscope.cn/models/vllm-ascend/Kimi-K2-Instruct-W8A8
|
||||
@@ -116,7 +115,6 @@ export TP_SOCKET_IFNAME=$nic_name
|
||||
export HCCL_SOCKET_IFNAME=$nic_name
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=100
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
|
||||
vllm serve /home/cache/weights/Kimi-K2-Instruct-W8A8 \
|
||||
|
||||
@@ -104,7 +104,6 @@ export HCCL_SOCKET_IFNAME="eth0"
|
||||
export DISAGGREGATED_PREFILL_RANK_TABLE_PATH="/path/to/your/generated/ranktable.json"
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
export VLLM_USE_V1=1
|
||||
|
||||
vllm serve /model/Qwen3-30B-A3B \
|
||||
--host 0.0.0.0 \
|
||||
@@ -144,7 +143,6 @@ export HCCL_SOCKET_IFNAME="eth0"
|
||||
export DISAGGREGATED_PREFILL_RANK_TABLE_PATH="/path/to/your/generated/ranktable.json"
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
export VLLM_USE_V1=1
|
||||
|
||||
vllm serve /model/Qwen3-30B-A3B \
|
||||
--host 0.0.0.0 \
|
||||
@@ -183,7 +181,6 @@ export HCCL_SOCKET_IFNAME="eth0"
|
||||
export DISAGGREGATED_PREFILL_RANK_TABLE_PATH="/path/to/your/generated/ranktable.json"
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
export VLLM_USE_V1=1
|
||||
|
||||
vllm serve /model/Qwen3-30B-A3B \
|
||||
--host 0.0.0.0 \
|
||||
|
||||
@@ -107,7 +107,6 @@ export HCCL_IF_IP=192.0.0.1
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -162,7 +161,6 @@ export HCCL_IF_IP=192.0.0.2
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -217,7 +215,6 @@ export HCCL_IF_IP=192.0.0.3
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=2048
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -274,7 +271,6 @@ export HCCL_IF_IP=192.0.0.4
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=2048
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -338,7 +334,6 @@ export HCCL_IF_IP=192.0.0.1
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -393,7 +388,6 @@ export HCCL_IF_IP=192.0.0.2
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -448,7 +442,6 @@ export HCCL_IF_IP=192.0.0.3
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=2048
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
@@ -505,7 +498,6 @@ export HCCL_IF_IP=192.0.0.4
|
||||
export GLOO_SOCKET_IFNAME="eth0" # network card name
|
||||
export TP_SOCKET_IFNAME="eth0"
|
||||
export HCCL_SOCKET_IFNAME="eth0"
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=2048
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=10
|
||||
|
||||
@@ -70,7 +70,6 @@ export TP_SOCKET_IFNAME=$nic_name
|
||||
export HCCL_SOCKET_IFNAME=$nic_name
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=100
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
|
||||
vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct \
|
||||
@@ -112,7 +111,6 @@ export TP_SOCKET_IFNAME=$nic_name
|
||||
export HCCL_SOCKET_IFNAME=$nic_name
|
||||
export OMP_PROC_BIND=false
|
||||
export OMP_NUM_THREADS=100
|
||||
export VLLM_USE_V1=1
|
||||
export HCCL_BUFFSIZE=1024
|
||||
|
||||
vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct \
|
||||
|
||||
@@ -82,7 +82,6 @@ The content of the multi_producer.sh script:
|
||||
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:$LD_LIBRARY_PATH
|
||||
export PYTHONPATH=$PYTHONPATH:/xxxxx/vllm
|
||||
export MOONCAKE_CONFIG_PATH="/xxxxxx/mooncake.json"
|
||||
export VLLM_USE_V1=1
|
||||
export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3
|
||||
export ACL_OP_INIT_MODE=1
|
||||
export ASCEND_BUFFER_POOL=4:8
|
||||
@@ -145,7 +144,6 @@ The content of multi_consumer.sh:
|
||||
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:$LD_LIBRARY_PATH
|
||||
export PYTHONPATH=$PYTHONPATH:/xxxxx/vllm
|
||||
export MOONCAKE_CONFIG_PATH="/xxxxx/mooncake.json"
|
||||
export VLLM_USE_V1=1
|
||||
export ASCEND_RT_VISIBLE_DEVICES=4,5,6,7
|
||||
export ACL_OP_INIT_MODE=1
|
||||
export ASCEND_BUFFER_POOL=4:8
|
||||
@@ -246,7 +244,6 @@ Content of mixed_department.sh:
|
||||
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:$LD_LIBRARY_PATH
|
||||
export PYTHONPATH=$PYTHONPATH:/xxxxx/vllm
|
||||
export MOONCAKE_CONFIG_PATH="/xxxxxx/mooncake.json"
|
||||
export VLLM_USE_V1=1
|
||||
export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3
|
||||
export ACL_OP_INIT_MODE=1
|
||||
export ASCEND_BUFFER_POOL=4:8
|
||||
|
||||
Reference in New Issue
Block a user