[V0 Deprecation] Remove VLLM_USE_V1 from docs and scripts (#26336)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -97,7 +97,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=0 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=0 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20001 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -118,7 +118,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=1 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=1 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20002 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -139,7 +139,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=2 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=2 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20003 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -160,7 +160,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=3 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=3 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20004 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -190,7 +190,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=0 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=0 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20001 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -211,7 +211,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=1 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=1 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20002 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -232,7 +232,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=2 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=2 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20003 \
|
||||
--tensor-parallel-size 1 \
|
||||
@@ -253,7 +253,7 @@ python3 disagg_proxy_p2p_nccl_xpyd.py &
|
||||
??? console "Command"
|
||||
|
||||
```shell
|
||||
VLLM_USE_V1=1 CUDA_VISIBLE_DEVICES=3 vllm serve {your model directory} \
|
||||
CUDA_VISIBLE_DEVICES=3 vllm serve {your model directory} \
|
||||
--host 0.0.0.0 \
|
||||
--port 20004 \
|
||||
--tensor-parallel-size 1 \
|
||||
|
||||
Reference in New Issue
Block a user