0
LLM model selection & deployment analysis tool for DeepSeek Harness: deployability, VRAM, TTFT, latency, throughput and power for 38 models × 20 GPUs/NPUs
$ dsh plugin --profile web add dsh-model-deploy
2
plugins
LLM model selection & deployment analysis tool for DeepSeek Harness: deployability, VRAM, TTFT, latency, throughput and power for 38 models × 20 GPUs/NPUs
$ dsh plugin --profile web add dsh-model-deployRoutes agent requests intelligently to appropriate models or services based on task requirements.
$ dsh plugin --profile web add dsh-agentic-router