Skip to content

GitLab

Commit 1f7b7ce3 authored by luopl's avatar luopl
Browse files

upload whl

parent a0dcaa80
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 5 deletions
README.md
View file @ 1f7b7ce3
...@@ -49,7 +49,7 @@ docker load -i pytorch2.9.1-ubuntu22.04-dtk26.04-0130-py3.10-20260204.tar.gz ...@@ -49,7 +49,7 @@ docker load -i pytorch2.9.1-ubuntu22.04-dtk26.04-0130-py3.10-20260204.tar.gz
- 挂载地址`-v` 根据实际模型情况修改 - 挂载地址`-v` 根据实际模型情况修改
```bash ```bash
docker run -it \ docker run -it \
--shm-size 60g \ --shm-size 200g \
--network=host \ --network=host \
--name qwen3.5 \ --name qwen3.5 \
--privileged \ --privileged \
...@@ -110,9 +110,6 @@ export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 ...@@ -110,9 +110,6 @@ export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
export VLLM_SPEC_DECODE_EAGER=1 export VLLM_SPEC_DECODE_EAGER=1
export VLLM_MLA_DISABLE=0 export VLLM_MLA_DISABLE=0
export VLLM_USE_FLASH_MLA=1 export VLLM_USE_FLASH_MLA=1
# K100_AI集群建议额外设置的环境变量：
export VLLM_ENFORCE_EAGER_BS_THRESHOLD=44
export VLLM_RPC_TIMEOUT=1800000 export VLLM_RPC_TIMEOUT=1800000
# 海光CPU绑定核 # 海光CPU绑定核
......
model.properties
View file @ 1f7b7ce3
...@@ -11,4 +11,4 @@ appCategory=对话问答 ...@@ -11,4 +11,4 @@ appCategory=对话问答
# 框架类型 # 框架类型
frameType=vllm frameType=vllm
# 加速卡类型 # 加速卡类型
accelerateType=K100AI,BW1000 accelerateType=BW1000
\ No newline at end of file \ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment