wordpress手机站如何做,那里做网站,怎样进行seo推广,广告设计专业就业前景好吗今天主要是结合理论进一步熟悉TensorRT-LLM的内容
从下面的分享可以看出#xff0c;TensorRT-LLM是在TensorRT的基础上进行了进一步封装#xff0c;提供拼batch#xff0c;量化等推理加速实现方式。 下面的图片更好的展示了TensorRT-LLM的流程#xff0c;包含权重转换TensorRT-LLM是在TensorRT的基础上进行了进一步封装提供拼batch量化等推理加速实现方式。 下面的图片更好的展示了TensorRT-LLM的流程包含权重转换构建Engine以及推理评估等内容。总结一下就是三步。 不想看图的话可以看看AI的总结,我放在附录中。
下图也很好的展示的trt-llm推理的全流程。 多卡并行
值得注意的是trt-llm特意考虑了多卡部署的使用场景。通过tp-size参数来控制张量并行的程度pp-size来控制溧水县并行的程度。 流水线并行 量化
权重激活值量化 KV Cache量化 量化精度影响
从下图可以看出使用FP8进行量化量化精度较高。 性能调优
关于性能调优trt-llm中也使用了类似于vllm中xontinuous batching的策略。 附录
The image describes an overview of the TensorRT-LLM (Large Language Model) workflow. Heres a summary of the key steps and elements involved:
1. Input Models: - Various external models from frameworks like **HuggingFace**, **NeMo**, **AMMO**, and **Jax** can be used as inputs.
2. TRT-LLM Checkpoint: - These external models are converted into a format defined by TRT-LLM using scripts like **convert_checkpoint.py** or **quantize.py**. - This conversion determines several key backward layer parameters, including: - Quantization method - Parallelization method - And more...
3. TRT-LLM Engines: - After converting to the checkpoint format, the **trtllm-build** command is used to further convert and optimize the checkpoint into **TensorRT Engines**. - During this step, important inference parameters are set, such as: - Max batch size - Max input length - Max output length - Max beam width - Plugin configuration - And others... - Most of the automatic optimizations occur at this stage.
4. Application Development: - Using C/Python APIs, developers can build applications with these optimized engines. - TensorRT-LLM comes with several built-in tools to help with secondary development: - **summarize.py** for text summarization - **mmlu.py** for accuracy testing - **run.py** for a dry run to verify the model - **benchmark** for benchmarking - The runtime options include: - **Temperature** (for sampling) - **Top K** (for top K sampling) - **Top P** (for nucleus sampling)
This workflow outlines how to integrate and optimize models for efficient inference with TensorRT-LLM and leverage its tools for application development and performance testing. NVIDIA AI 加速精讲堂-TensorRT-LLM 应用与部署_哔哩哔哩_bilibili
