FasterTransformer
server
FasterTransformer | server | |
---|---|---|
7 | 24 | |
5,506 | 7,414 | |
2.1% | 3.4% | |
4.3 | 9.5 | |
about 2 months ago | 3 days ago | |
C++ | Python | |
Apache License 2.0 | 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.
FasterTransformer
-
Train Your AI Model Once and Deploy on Any Cloud
https://docs.nvidia.com/ai-enterprise/overview/0.1.0/platfor...
RIVA: NVIDIA® Riva, a premium edition of NVIDIA AI Enterprise software, is a GPU-accelerated speech and translation AI SDK
FasterTransformer: https://github.com/NVIDIA/FasterTransformer an
-
Whether the ML computation engineering expertise will be valuable, is the question.
There could be some spectrum of this expertise. For instance, https://github.com/NVIDIA/FasterTransformer, https://github.com/microsoft/DeepSpeed
-
Optimized implementation of training/fine-tuning of LLMs [D]
Have anyone tried to optimize the forward and backward using custom Cuda code or fused kernel to speed up the training time of current LLMs? I only have seen FasterTransformer ( NVIDIA/FasterTransformer) and other similar tools but they're only focusing on inference.
-
Exploring Ghostwriter, a GitHub Copilot alternative
Replit built Ghostwriter on the open source scene based on Salesforce’s Codegen, using Nvidia’s FasterTransformer and Triton server for highly optimized decoders, and the knowledge distillation process of the CodeGen model from two billion parameters to a faster model of one billion parameters.
- Why are self attention not as deployment friendly?
-
[P] What we learned by making T5-large 2X faster than Pytorch (and any autoregressive transformer)
Nvidia FasterTransformer is a mix of Pytorch and CUDA/C++ dedicated code. The performance boost is huge on T5, they report a 10X speedup like TensorRT. However, the speedup is computed on a translation task where sequences are 25 tokens long on average. In our experience, improvement on very short sequences tend to decrease by large margins on longer ones. Still we plan to dig deeper into this project as it implements very interesting ideas.
-
[P] Python library to optimize Hugging Face transformer for inference: < 0.5 ms latency / 2850 infer/sec
On the other side of the spectrum, there is Nvidia demos (here or there) showing us how to build manually a full Transformer graph (operator by operator) in TensorRT to get best performance from their hardware. It’s out of reach for many NLP practitioners and it’s time consuming to debug/maintain/adapt to a slightly different architecture (I tried). Plus, there is a secret: the very optimized model only works for specific sequence lengths and batch sizes. Truth is that, so far (and it will improve soon), it’s mainly for MLPerf benchmark (the one used to compare DL hardware), marketing content, and very specialized engineers.
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
What are some alternatives?
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx-tensorrt - ONNX-TensorRT: TensorRT backend for ONNX
transformer-deploy - Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
parallelformers - Parallelformers: An Efficient Model Parallelization Toolkit for Deployment
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
wenet - Production First and Production Ready End-to-End Speech Recognition Toolkit
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