update

README.md

@@ -14,4 +14,5 @@
 - Qwen/Qwen2.5-7B-instruct
 - Qwen/Qwen2-VL-2B-Instruct
 - ZhipuAI/glm-4v-9b
-- LLM-Research/gemma-3-27b-it
+- LLM-Research/gemma-3-27b-it
+- stepfun-ai/step3

enginex/step3.md

@@ -0,0 +1,8 @@
+# 运行方式
+
+```python
+docker pull git.modelhub.org.cn:9443/enginex-hygon/custom:vllm-ubuntu22.04-dtk25.04.1-rc5-das1.6-py3.10-20250802-step3
+docker run -it --name step_vllm --shm-size=1024G  --device=/dev/kfd --device=/dev/dri/ --privileged --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v /opt/hyhal:/opt/hyhal:ro -v $PWD/Step3_pytorch:/home/Step3_pytorch f0e4191089de /bin/bash
+wget --content-disposition 'https://download.sourcefind.cn:65024/file/4/triton/DAS1.6/triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl'
+pip install triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
+```