server
storium-backend
server | storium-backend | |
---|---|---|
24 | 4 | |
7,356 | 8 | |
2.7% | - | |
9.5 | 0.0 | |
4 days ago | about 2 years ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | BSD 3-clause "New" or "Revised" License |
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.
server
- FLaNK Weekly 08 Jan 2024
- Is there any open source app to load a model and expose API like OpenAI?
- "A matching Triton is not available"
-
best way to serve llama V2 (llama.cpp VS triton VS HF text generation inference)
I am wondering what is the best / most cost-efficient way to serve llama V2. - llama.cpp (is it production ready or just for playing around?) ? - Triton inference server ? - HF text generation inference ?
- Triton Inference Server - Backend
-
Single RTX 3080 or two RTX 3060s for deep learning inference?
For inference of CNNs, memory should really not be an issue. If it is a software engineering problem, not a hardware issue. FP16 or Int8 for weights is fine and weight size won’t increase due to the high resolution. And during inference memory used for hidden layer tensors can be reused as soon as the last consumer layer has been processed. You likely using something that is designed for training for inference and that blows up the memory requirement, or if you are using TensorRT or something like that, you need to be careful to avoid that every tasks loads their own copy of the library code into the GPU. Maybe look at https://github.com/triton-inference-server/server
-
Machine Learning Inference Server in Rust?
I am looking for something like [Triton Inference Server](https://github.com/triton-inference-server/server) or [TFX Serving](https://www.tensorflow.org/tfx/guide/serving), but in Rust. I came across [Orkon](https://github.com/vertexclique/orkhon) which seems to be dormant and a bunch of examples off of the [Awesome-Rust-MachineLearning](https://github.com/vaaaaanquish/Awesome-Rust-MachineLearning)
-
Multi-model serving options
You've already mentioned Seldon Core which is well worth looking at but if you're just after the raw multi-model serving aspect rather than a fully-fledged deployment framework you should maybe take a look at the individual inference servers: Triton Inference Server and MLServer both support multi-model serving for a wide variety of frameworks (and custom python models). MLServer might be a better option as it has an MLFlow runtime but only you will be able to decide that. There also might be other inference servers that do MMS that I'm not aware of.
-
I mean,.. we COULD just make our own lol
[1] https://docs.nvidia.com/launchpad/ai/chatbot/latest/chatbot-triton-overview.html[2] https://github.com/triton-inference-server/server[3] https://neptune.ai/blog/deploying-ml-models-on-gpu-with-kyle-morris[4] https://thechief.io/c/editorial/comparison-cloud-gpu-providers/[5] https://geekflare.com/best-cloud-gpu-platforms/
-
Why TensorFlow for Python is dying a slow death
"TensorFlow has the better deployment infrastructure"
Tensorflow Serving is nice in that it's so tightly integrated with Tensorflow. As usual that goes both ways. It's so tightly coupled to Tensorflow if the mlops side of the solution is using Tensorflow Serving you're going to get "trapped" in the Tensorflow ecosystem (essentially).
For pytorch models (and just about anything else) I've been really enjoying Nvidia Triton Server[0]. Of course it further entrenches Nvidia and CUDA in the space (although you can execute models CPU only) but for a deployment today and the foreseeable future you're almost certainly going to be using a CUDA stack anyway.
Triton Server is very impressive and I'm always surprised to see how relatively niche it is.
[0] - https://github.com/triton-inference-server/server
storium-backend
-
[R] Wordcraft: a Human-AI Collaborative Editor for Story Writing
I’m excited to see where research like this goes next. Though I’m biased considering my research on Storium.
-
[D] Very long sequence data (books) understanding?
I released a dataset of stories that are 19K tokens on average, but the longest are over a million. Our human evaluations show that relevance is the biggest factor in whether authors decide to use model generated text in their story, making this a good platform for assessing long document understanding and generation.
-
[P] Question about generating stories
More recent work tries to learn all of this purely from text. My dataset collected from Storium includes a narrator and annotations, e.g. challenges, goals, etc that can help learn these traits directly from the dataset.
-
[D] Deploying ML models - batching
If you’re willing to roll your own, you can see an example from my latest research project that makes use of asyncio.
What are some alternatives?
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Cornucopia-LLaMA-Fin-Chinese - 聚宝盆(Cornucopia): 中文金融系列开源可商用大模型,并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
onnx-tensorrt - ONNX-TensorRT: TensorRT backend for ONNX
Spectrum - Spectrum is an AI that uses machine learning to generate Rap song lyrics
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
commit-autosuggestions - A tool that AI automatically recommends commit messages.
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
GPT2-Chinese - Chinese version of GPT2 training code, using BERT tokenizer.
Triton - Triton is a dynamic binary analysis library. Build your own program analysis tools, automate your reverse engineering, perform software verification or just emulate code.
Megatron-LM - Ongoing research training transformer models at scale
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
tensorflow - An Open Source Machine Learning Framework for Everyone