serve
optimum
Our great sponsors
serve | optimum | |
---|---|---|
11 | 8 | |
3,941 | 2,132 | |
1.5% | 4.6% | |
9.6 | 9.5 | |
7 days ago | 3 days ago | |
Java | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
serve
-
Show Show HN: Llama2 Embeddings FastAPI Server
What's wrong with just using Torchserve[1]? We've been using it to serve embedding models in production.
-
How to leverage a local LLM for a client?
Looks like you are already up to speed loading LLaMa models which is great. Assuming this is Hugging Face PyTorch checkpoint, I think it should be possible to spin up a TorchServe instance which has in-built support for API access and HF Transformers. Since scale and latency aren’t a big concern for you, this should be good enough start.
- Is there a course that teaches you how to make an API with a trained model?
-
Pytorch eating memory on every api call
You could split the service in two, flask for the web part and a service to serve the model, I haven't used it but there is https://pytorch.org/serve/
-
Google Kubernetes Engine : Unable to access ports exposed on external IP
I'm attempting to set up inference for a torchserve container, and it's really tough to figure out what's not allowing me to connect to my network with the ports that I'm trying to expose. I'm using Google Kubernetes Engine and Helm via tweaking one of the tutorials at [torchserve](github.com/pytorch/serve). Specifically, it's the GKE tutorial [here](https://github.com/pytorch/serve/tree/master/kubernetes).
-
BetterTransformer: PyTorch-native free-lunch speedups for Transformer-based models
I did a Space to showcase a bit the speedups we can have in a end-to-end case with TorchServe to deploy the model on a cloud instance (AWS EC2 g4dn, using one T4 GPU): https://huggingface.co/spaces/fxmarty/bettertransformer-demo
-
[D] How to get the fastest PyTorch inference and what is the "best" model serving framework?
For 2), I am aware of a few options. Triton inference server is an obvious one as is the ‘transformer-deploy’ version from LDS. My only reservation here is that they require the model compilation or are architecture specific. I am aware of others like Bento, Ray serving and TorchServe. Ideally I would have something that allows any (PyTorch model) to be used without the extra compilation effort (or at least optionally) and has some convenience things like ease of use, easy to deploy, easy to host multiple models and can perform some dynamic batching. Anyway, I am really interested to hear people's experience here as I know there are now quite a few options! Any help is appreciated! Disclaimer - I have no affiliation or are connected in any way with the libraries or companies listed here. These are just the ones I know of. Thanks in advance.
-
how to integrate a deep learning model into a Django webapp!?
If you built the model using pytorch or tensorflow, I'd suggest using torchserve or TF serving to serve the model as its own "microservice," then query it from your django app. Among other things, it will make retraining and updating your model a lot easier.
- Choose JavaScript ðŸ§
-
Popular Machine Learning Deployment Tools
GitHub
optimum
-
FastEmbed: Fast and Lightweight Embedding Generation for Text
Shout out to Huggingface's Optimum – which made it easier to quantize models.
-
[D] Is ML doomed to end up closed-source?
Optimum to accelerate inference of transformers with hardware optimization
-
[P] BetterTransformer: PyTorch-native free-lunch speedups for Transformer-based models
Yes Optimum lib's documentation is unfortunately not yet in best shape. I would be really thankful if you fill an issue detailing where the doc can be improved: https://github.com/huggingface/optimum/issues . Also, if you have features request, such as having a more flexible API, we are eager for community contributions or suggestions!
-
BetterTransformer: PyTorch-native free-lunch speedups for Transformer-based models
In order to support BetterTransformer with the canonical Transformer models from Transformers library, an integration was done with the open-source library Optimum as a one-liner:
- Why are self attention not as deployment friendly?
-
[P] Accelerated Inference with Optimum and Transformers Pipelines
It’s Lewis here from the open-source team at Hugging Face 🤗. I'm excited to share the latest release of our Optimum library, which provides a suite of performance optimization tools to make Transformers run fast on accelerated hardware!
-
[N] Hugging Face raised $100M at $2B to double down on community, open-source & ethics
Create libraries to optimize ML models during training and inference for specific hardware https://github.com/huggingface/optimum
-
[P] Python library to optimize Hugging Face transformer for inference: < 0.5 ms latency / 2850 infer/sec
Have you seen this article from HF https://huggingface.co/blog/bert-cpu-scaling-part-2 , there is also a lib https://github.com/huggingface/optimum? is the gain worth the tweaking? is OneDNN stuff easy to deploy on Triton?
What are some alternatives?
server - The Triton Inference Server provides an optimized cloud and edge inferencing solution.
FasterTransformer - Transformer related optimization, including BERT, GPT
serving - A flexible, high-performance serving system for machine learning models
transformer-deploy - Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
JavaScriptClassifier - [Moved to: https://github.com/JonathanSum/JavaScriptClassifier]
safetensors - Simple, safe way to store and distribute tensors
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
kernl - Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
text-generation-inference - Large Language Model Text Generation Inference
deepsparse - Sparsity-aware deep learning inference runtime for CPUs