Embedl-optimized · TensorRT Edge-LLM
- huggingface
- AGX Orin
- Labels
- Text
- LLM
- Generation
- Build
- Embedl-optimized
- Precision
- W4A16
- Runtime
- TensorRT Edge-LLM 0.10.1 with Embedl optimizations
- Context length
- 4,096 tokens
Nous Research's Hermes 3, a fine-tune of Llama 3.1 8B for chat, role-play, function calling and structured output.
Methodology
- Throughput: one user, real conversations from the public OpenAssistant set, 2,048 tokens in, 128 out, greedy, no prompt reuse. Average of 20 requests after 3 warm-up requests. End-to-end is the whole request. Prompt processing is the 2,048 prompt tokens over the time to first token.
- Power and memory: sampled on the device during those runs. Idle is the device at rest with the model loaded; energy per token is the run's energy over its generated tokens; peak memory is the device's.
- Accuracy: full test sets, greedy, the same model files and settings as served. GSM8K 1319, IFEval 541, MMLU-Pro 1008 questions.
- Baseline TensorRT Edge-LLM: the original FP16 model on upstream TensorRT Edge-LLM, same settings, same device.