neural-nova
/

GLM-5.2-Instruct-Optimized

inference-optimization

Mixture of Experts

Model card Files Files and versions

GLM-5.2-Instruct-Optimized / Dockerfile

NeuralNovaAI's picture

Create Dockerfile

f268dfe verified 15 days ago

Raw History Blame Contribute Delete

209 Bytes

	FROM vllm/vllm-openai-rocm:v0.25.1

	WORKDIR /workspace
	COPY launch_server.sh run_benchmark.sh ./
	RUN chmod +x launch_server.sh run_benchmark.sh

	EXPOSE 8000
	ENTRYPOINT ["./launch_server.sh"]
	CMD ["optimized"]