update vllm

README.md

@@ -9,19 +9,44 @@
 
 支持模型列表：
 - jina-embeddings-v3
-- DeepSeek-R1_ollama
-- DeepSeek-R1_pytorch
-- DeepSeek-R1-Distill
-- ChatGLM3-6B
-- QwQ-32B
-- DeepSeek-V3
+- deepseek-ai/DeepSeek-R1
+- Qwen/QwQ-32B
+- deepseek-ai/DeepSeek-V3
+- deepseek-ai/DeepSeek-V3.1
 - LLaMA_Fastchat_pytorch
 - Qwen3
-- Qwen3-30B-A3B_vllm
+- Qwen/Qwen3-30B-A3B
 - Qwen-7B_fastllm
 - ChatGLM-6B_fastllm
-- ChatGLM-6B_pytorch
+- ZhipuAI/ChatGLM-6B
 - Shanghai_AI_Laboratory/internlm-chat-7b
 - ZhipuAI/glm-4v-9b
 - ZhipuAI/GLM-4-9B-0414
 - deepseek-ai/DeepSeek-Coder-V2-Base
+- openai-community/gpt2
+- ZhipuAI/chatglm2-6b
+- Qwen/Qwen-7B-Chat
+- baichuan-inc/Baichuan2-13B-Chat
+- ZhipuAI/chatglm3-6b
+- deepseek-ai/DeepSeek-V2
+- Qwen/Qwen2.5-Omni-7B
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+- LLM-Research/Meta-Llama-3-8B-Instruct
+- Qwen/Qwen1.5-14B-Chat
+- Qwen/Qwen2-7B
+- Qwen/Qwen3-Embedding-0.6B
+- baichuan-inc/baichuan-7B
+- openai-community/gpt2
+- gaodema/GME-Qwen2-VL
+- OpenBMB/MiniCPM3-4B
+- ZhipuAI/glm-10b-chinese
+- 01ai/Yi-6B-Chat
+- 01ai/Yi-34B-Chat
+
+
+

enginex/DeepSeek-V2.md

@@ -0,0 +1,8 @@
+# 运行方式
+```python
+docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-centos7.6-dtk24.04-py310
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/deepseek-v2_pytorch
+pip install -r requirements.txt
+```

enginex/DeepSeek-V3.1.md

@@ -0,0 +1,8 @@
+# 运行方式
+```python
+docker pull git.modelhub.org.cn:9443/enginex-hygon/vllm:0.9.2-ubuntu22.04-dtk25.04.1-rc5-rocblas101839-0811-das1.6-py3.10-20250812-beta
+
+docker run -it --name {docker_name} --device=/dev/kfd --privileged --network=host --device=/dev/dri --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /your_code_path:/your_code_path -v /opt/hyhal:/opt/hyhal:ro -v /module/DeepSeek-V3.1:/your_model_path/DeepSeek-V3.1 --group-add video --shm-size 64G {imageID} bash
+
+cd /your_code_path/deepseek-v3.1_vllm
+```

enginex/Meta-Llama-3-8B-Instruct.md

@@ -2,5 +2,9 @@
 
 ```python
 #  推荐使用docker方式运行，提供拉取的docker镜像：
-docker pull git.modelhub.org.cn:9443/enginex-hygon/
+docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-centos7.6-dtk24.04-py310
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/llama3_pytorch
+pip install -e .
 ```

enginex/Qwen3-Embedding-0.6B.md

@@ -1,5 +1,10 @@
 # 运行方式
 
 ```python
-docker pull git.modelhub.org.cn:9443/enginex-hygon/
+docker pull git.modelhub.org.cn:9443/enginex-hygon/custom:vllm0.8.5-ubuntu22.04-dtk25.04-rc7-das1.5-py3.10-20250521-fixpy-rocblas0521-beta2
+docker run -it --shm-size 200g --network=host --name {docker_name} --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro {imageID} bash
+
+cd /your_code_path/qwen3-embedding_pytorch
+pip install transformers>=4.51.0
+pip install sentence-transformers>=2.7.0
 ```

enginex/Qwen3_副本.md

@@ -1,9 +0,0 @@
-# 运行方式
-
-```python
-docker pull git.modelhub.org.cn:9443/enginex-hygon/custom:vllm0.8.4-ubuntu22.04-dtk25.04-rc7-das1.5-py3.10-20250429-dev-qwen3-only
-# <your IMAGE ID>为以上拉取的docker的镜像ID替换
-docker run -it --shm-size=64G -v $PWD/Qwen3:/home/Qwen3 -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name qwen3 <your IMAGE ID> bash
-cd /home/Qwen3
-pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
-```

enginex/Yi-34B-Chat.md

@@ -0,0 +1,9 @@
+# 运行方式
+
+```python
+docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
+# <img id="">用上面拉取docker镜像的ID替换
+# 主机端路径
+# 容器映射路径
+docker run -it --name yi --shm-size=64G  --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /opt/hyhal:/opt/hyhal:ro --ulimit memlock=-1:-1 --ipc=host --network=host --group-add video -v : <img id=""> /bin/bash
+```

enginex/Yi-6B-Chat.md

@@ -1,10 +1,9 @@
 # 运行方式
 
 ```python
-docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-py3.10-dtk24.04.3-ubuntu20.04
-docker run -it --shm-size=1024G -v : -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name Yi-1.5   bash  # 为以上拉取的docker的镜像ID替换
-cd /home/Yi-1.5-pytorch
-pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com
-
-pip uninstall vllm
+docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
+# <img id="">用上面拉取docker镜像的ID替换
+# 主机端路径
+# 容器映射路径
+docker run -it --name yi --shm-size=64G  --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /opt/hyhal:/opt/hyhal:ro --ulimit memlock=-1:-1 --ipc=host --network=host --group-add video -v : <img id=""> /bin/bash
 ```

enginex/gpt2.md

@@ -0,0 +1,8 @@
+# 运行方式
+
+```python
+docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:1.10.0-centos7.6-dtk-23.04-py37-latest
+docker run -dit --network=host --name=gpt2_pytorch --privileged --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size=16G  --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root --ulimit stack=-1:-1 --ulimit memlock=-1:-1 image.sourcefind.cn:5000/dcu/admin/base/pytorch:1.10.0-centos7.6-dtk-23.04-py37-latest
+docker exec -it gpt2_pytorch /bin/bash
+pip install -r requirements.txt  -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com
+```