#
1a1a11a
Follow
Lists (2)
Starred repositories
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
Composable building blocks to build Llama Apps
New file format for storage of large columnar datasets.
A C implementation of the SIEVE cache eviction algorithm, based on the research paper (https://junchengyang.com/publication/nsdi24-SIEVE.pdf)
a distributed computation platform for running Python and Bash computation tasks on multiple nodes
[NeurIPS 2024] FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
PyTorch per step fault tolerance (actively under development)
VideoSys: An easy and efficient system for video generation
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A cheatsheet of modern C++ language and library features.
[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
DCPerf benchmark suite for hyperscale cloud applications
[CVPR 2023] DepGraph: Towards Any Structural Pruning
Tools for profiling the Linux network stack.
Minimalistic large language model 3D-parallelism training
llama3 implementation one matrix multiplication at a time
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
grep for words with similar meaning to the query
A simple, high-throughput file client for mounting an Amazon S3 bucket as a local file system.
Implementation of a new caching algo called SIEVE. Link to paper included in README
Retrieval and Retrieval-augmented LLMs
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.