tinygrad
LevelDB
| tinygrad | LevelDB | |
|---|---|---|
| 58 | 27 | |
| 17,800 | 35,186 | |
| - | 0.9% | |
| 9.7 | 0.0 | |
| 10 months ago | 17 days ago | |
| Python | C++ | |
| MIT 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.
tinygrad
- tinygrad: extreme simplicity, easiest framework to add new accelerators to
-
GGML – AI at the Edge
Might be a silly question but is GGML a similar/competing library to George Hotz's tinygrad [0]?
[0] https://github.com/geohot/tinygrad
-
Render neural network into CUDA/HIP code
at first glance i thought may its like tinygrad. but looks has many ops than that tiny grad but most maps to underlying hardware provided ops?
i wonder how well tinygrad's apporach will work out, ops fusion sounds easy, just a walk a graph, pattern match it and lower to hardware provided ops?
Anyway if anyone wants to understand the philosophy behind tinygrad, this file is great start https://github.com/geohot/tinygrad/blob/master/docs/abstract...
-
llama.cpp now officially supports GPU acceleration.
There are currently at least 3 ways to run llama on m1 with GPU acceleration. - mlc-llm (pre-built, only 1 model has been ported) - tinygrad (very memory efficient, not that easy to integrate into other projects) - llama-mps (original llama codebase + llama adapter support)
- George Hotz building an AMD competitor to Nvidia.
-
George Hotz ROCm adventures
Hopefully we will see now full support with AMD hardware on https://github.com/geohot/tinygrad. You can read more about it on https://tinygrad.org/
-
The Coming of Local LLMs
tinygrad
https://github.com/geohot/tinygrad/tree/master/accel/ane
But I have not tested it on Linux since Asahi has not yet added support.
llama.cpp runs at 18ms per token (7B) and 200ms per token (65B) without quantization.
- Everything we know about Apple's Neural Engine
- Everything we know about the Apple Neural Engine (ANE)
- How 'Open' Is OpenAI, Really?
LevelDB
-
Codebases to read
I'm partial to how cleanly written https://github.com/google/leveldb is. It is a reasonable size to fully read & grok in not too long.
-
Unpacking LSM-Trees: The Powerhouse Behind Modern Databases
[4] leveldb/doc/impl.md at main · google/leveldb. GitHub. Retrieved October 21, 2023 from https://github.com/google/leveldb/blob/main/doc/impl.md
- Bloom filter support to leveldb by Sanjay Ghemawat
- SQLite performance tuning: concurrent reads, multiple GBs and 100k SELECTs/s
-
The Witty Guide to Installing LevelDB on Ubuntu: HostRooster® Edition
git clone https://github.com/google/leveldb.git
-
Is there a lightweight, stable and embedded database library?
leveldb?
- Ask HN: What's the best source code you've read?
-
LevelDB VS ZoneTree - a user suggested alternative
2 projects | 22 Aug 2022
- Is Mongo as popular in the job world as it is with tutorial makers?
-
Open Source Databases in Go
goleveldb - Implementation of the LevelDB key/value database in Go.
What are some alternatives?
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
RocksDB - A library that provides an embeddable, persistent key-value store for fast storage.
llama.cpp - LLM inference in C/C++
MongoDB - The MongoDB Database
openpilot - openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.
Redis - Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs, Bitmaps.
llama - Inference code for Llama models
SQLite - Unofficial git mirror of SQLite sources (see link for build instructions)
tensorflow_macos - TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
LMDB - Read-only mirror of official repo on openldap.org. Issues and pull requests here are ignored. Use OpenLDAP ITS for issues.
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
CouchDB - Seamless multi-master syncing database with an intuitive HTTP/JSON API, designed for reliability