base on <div align="center"> Optimum-NVIDIA =========================== <h4> Optimized inference with NVIDIA and Hugging Face </h4> [](https://huggingface.co/docs/optimum/index) [](https://www.python.org/downloads/release/python-31013/) [](https://developer.nvidia.com/cuda-downloads) [](https://github.com/nvidia/tensorrt-llm) [](./LICENSE) --- <div align="left"> Optimum-NVIDIA delivers the best inference performance on the NVIDIA platform through Hugging Face. Run LLaMA 2 at 1,200 tokens/second (up to 28x faster than the framework) by changing just a single line in your existing transformers code. </div></div> # Installation ## Pip Pip installation flow has been validated on Ubuntu only at this stage. ```shell apt-get update && apt-get -y install python3.10 python3-pip openmpi-bin libopenmpi-dev python -m pip install --pre --extra-index-url https://pypi.nvidia.com optimum-nvidia ``` For developers who want to target the best performances, please look at the installation methods below. ## Docker container You can use a Docker container to try Optimum-NVIDIA today. Images are available on the Hugging Face Docker Hub. ```bash docker pull huggingface/optimum-nvidia ``` ## Building from source <!--- Currently, TRT LLM is built and run with Docker, so we should wait until pip installation is available; Ideally the user doesn't need to use docker at all to build from source, they should be able to run something like `git clone [...] && pip install -e optimum-nvidia` --> Instead of using the pre-built docker container, you can build Optimum-NVIDIA from source: ```bash TARGET_SM="90-real;89-real" git clone --recursive --depth=1 https://github.com/huggingface/optimum-nvidia.git cd optimum-nvidia/third-party/tensorrt-llm make -C docker release_build CUDA_ARCHS=$TARGET_SM cd ../.. && docker build -t <organisation_name/image_name>:<version> -f docker/Dockerfile . ``` <!-- ```bash git clone [email protected]:huggingface/optimum-nvidia.git cd optimum-nvidia docker build Dockerfile docker run optimum-nvidia ``` --> # Quickstart Guide ## Pipelines Hugging Face pipelines provide a simple yet powerful abstraction to quickly set up inference. If you already have a pipeline from transformers, you can unlock the performance benefits of Optimum-NVIDIA by just changing one line. ```diff - from transformers.pipelines import pipeline + from optimum.nvidia.pipelines import pipeline pipe = pipeline('text-generation', 'meta-llama/Llama-2-7b-chat-hf', use_fp8=True) pipe("Describe a real-world application of AI in sustainable energy.") ``` ## Generate If you want control over advanced features like quantization and token selection strategies, we recommend using the `generate()` API. Just like with `pipelines`, switching from existing transformers code is super simple. ```diff - from transformers import AutoModelForCausalLM + from optimum.nvidia import AutoModelForCausalLM from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", padding_side="left") model = AutoModelForCausalLM.from_pretrained( "meta-llama/Llama-2-7b-chat-hf", + use_fp8=True, + max_prompt_length=1024, + max_output_length=2048, # Must be at least size of max_prompt_length + max_new_tokens + max_batch_size=8, ) model_inputs = tokenizer(["How is autonomous vehicle technology transforming the future of transportation and urban planning?"], return_tensors="pt").to("cuda") generated_ids = model.generate( **model_inputs, top_k=40, top_p=0.7, repetition_penalty=10, ) tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` To learn more about text generation with LLMs, check out [this guide](https://huggingface.co/docs/transformers/llm_tutorial)! <!-- For more details, read our [documentation](https://huggingface.com/docs/optimum/nvidia/index). --> # Support Matrix We test Optimum-NVIDIA on 4090, L40S, and H100 Tensor Core GPUs, though it is expected to work on any GPU based on the following architectures: * Ampere (A100/A30 are supported. Experimental support for A10, A40, RTX Ax000) * Hopper * Ada-Lovelace Note that FP8 support is only available on GPUs based on Hopper and Ada-Lovelace architectures. Optimum-NVIDIA works on Linux will support Windows soon. Optimum-NVIDIA currently accelerates text-generation with LLaMAForCausalLM, and we are actively working to expand support to include more model architectures and tasks. <!-- Optimum-NVIDIA supports the following model architectures and tasks: | Model | Tasks | | :---- | :---- | | Gemma | TextGeneration | | Llama | TextGeneration | | Mistral | TextGeneration | | Additional Models | Coming soon | --> # Contributing Check out our [Contributing Guide](./CONTRIBUTING.md) ", Assign "at most 3 tags" to the expected json: {"id":"5746","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"