Ray
determined
Ray | determined | |
---|---|---|
43 | 10 | |
31,179 | 2,868 | |
1.8% | 2.3% | |
10.0 | 9.9 | |
1 day ago | 1 day ago | |
Python | Go | |
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.
Ray
- Ray: Unified framework for scaling AI and Python applications
-
Open Source Advent Fun Wraps Up!
22. Ray | Github | tutorial
-
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models
Training times for GSM8k are mentioned here: https://github.com/ray-project/ray/tree/master/doc/source/te...
- Ray – an open source project for scaling AI workloads
-
Methods to keep agents inside grid world.
Here's a reference from RLlib that points to docs and an example, and here's one from one of my projects that includes all my own implementations
-
TransformerXL + PPO Baseline + MemoryGym
RLlib
- Is dynamic action masking possible in Rllib?
-
AWS re:Invent 2022 Recap | Data & Analytics services
⦿ AWS Glue Data Quality - Automatic data quality rule recommendations based on your data AWS Glue for Ray - Data integration with Ray (ray.io), a popular new open-source compute framework that helps you scale Python workloads
-
Think about it for a second
https://ray.io (just dropping the link)
-
Elixir Livebook now as a desktop app
I've wondered whether it's easier to add data analyst stuff to Elixir that Python seems to have, or add features to Python that Erlang (and by extension Elixir) provides out of the box.
By what I can see, if you want multiprocessing on Python in an easier way (let's say running async), you have to use something like ray core[0], then if you want multiple machines you need redis(?). Elixir/Erlang supports this out of the box.
Explorer[1] is an interesting approach, where it uses Rust via Rustler (Elixir library to call Rust code) and uses Polars as its dataframe library. I think Rustler needs to be reworked for this usecase, as it can be slow to return data. I made initial improvements which drastically improves encoding (https://github.com/elixir-nx/explorer/pull/282 and https://github.com/elixir-nx/explorer/pull/286, tldr 20+ seconds down to 3).
[0] https://github.com/ray-project/ray
determined
-
Open Source Advent Fun Wraps Up!
17. Determined AI | Github | tutorial
-
ML Experiments Management with Git
Use Determined if you want a nice UI https://github.com/determined-ai/determined#readme
- Determined: Deep Learning Training Platform
-
Queueing/Resource Management Solutions for Self Hosted Workstation?
I looked up and found [Determined Platform](determined.ai), tho it looks a very young project that I don't know if it's reliable enough.
-
Ask HN: Who is hiring? (June 2022)
- Developer Support Engineer (~1/3 client facing, triaging feature requests and bug reports, etc; 2/3 debugging/troubleshooting)
We are developing enterprise grade artificial intelligence products/services for AI engineering teams and fortune 500 companies and need more software devs to fill the increasing demand.
Find out more at https://determined.ai/. If AI piques your curiosity or you want to interface with highly skilled engineers in the community, apply within (search "determined ai" at careers.hpe.com and drop me a message at asnell AT hpe PERIOD com).
-
How to train large deep learning models as a startup
Check out Determined https://github.com/determined-ai/determined to help manage this kind of work at scale: Determined leverages Horovod under the hood, automatically manages cloud resources and can get you up on spot instances, T4's, etc. and will work on your local cluster as well. Gives you additional features like experiment management, scheduling, profiling, model registry, advanced hyperparameter tuning, etc.
Full disclosure: I'm a founder of the project.
-
[D] managing compute for long running ML training jobs
These are some of the problems we are trying to solve with the Determined training platform. Determined can be run with or without k8s - the k8s version inherits some of the scheduling problems of k8s, but the non-k8s version uses a custom gang scheduler designed for large scale ML training. Determined offers a priority scheduler that allows smaller jobs to run while being able to schedule a large distributed job whenever you need, by setting a higher priority.
-
Cerebras’ New Monster AI Chip Adds 1.4T Transistors
Ah I see - I think we're pretty much on the same page in terms of timetables. Although if you include TPU, I think it's fair to say that custom accelerators are already a moderate success.
Updated my profile. I've been working on DL training platforms and distributed training benchmarking for a bit so I've gotten a nice view into the GPU/TPU battle.
Shameless plug: you should check out the open-source training platform we are building, Determined[1]. One of the goals is to take our hard-earned expertise on training infrastructure and build a tool where people don't need to have that infrastructure expertise. We don't support TPUs, partially because a lack of demand/TPU availability, and partially because our PyTorch TPU experiments were so unimpressive.
[1] GH: https://github.com/determined-ai/determined, Slack: https://join.slack.com/t/determined-community/shared_invite/...
-
[D] Software stack to replicate Azure ML / Google Auto ML on premise
Take a look at Determined https://github.com/determined-ai/determined
-
AWS open source news and updates No.41
determined is an open-source deep learning training platform that makes building models fast and easy. This project provides a CloudFormation template to bootstrap you into AWS and then has a number of tutorials covering how to manage your data, train and then deploy inference endpoints. If you are looking to explore more open source machine learning projects, then check this one out.
What are some alternatives?
optuna - A hyperparameter optimization framework
ColossalAI - Making large AI models cheaper, faster and more accessible
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Dagger.jl - A framework for out-of-core and parallel execution
Faust - Python Stream Processing
aws-virtual-gpu-device-plugin - AWS virtual gpu device plugin provides capability to use smaller virtual gpus for your machine learning inference workloads
gevent - Coroutine-based concurrency library for Python
cfn-diagram - CLI tool to visualise CloudFormation/SAM/CDK stacks as visjs networks, draw.io or ascii-art diagrams.
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
goofys - a high-performance, POSIX-ish Amazon S3 file system written in Go
SCOOP (Scalable COncurrent Operations in Python) - SCOOP (Scalable COncurrent Operations in Python)
alpa - Training and serving large-scale neural networks with auto parallelization.