Pinned Repositories
FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
cs61-2018-material
flashinfer
FlashInfer: Kernel Library for LLM Serving
LetsMeet
Let'sMeet! is a tool that enables users to instantly find people with whom they can study, eat lunch, and do other activities -- all without worrying about bothering people who don’t happen to be available to study or hang out at the same time as you.
LetsMeetBackend
This repository contains the server-side PHP Rest API used by my iOS app 'Let's Meet!'
moe_inference
ms_thesis
specinfer-ae
PyGithub
Typed interactions with the GitHub API v3
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
goliaro's Repositories
goliaro/specinfer-ae
goliaro/cmake-build-extension
Setuptools extension to build and package CMake projects
goliaro/flashinfer
FlashInfer: Kernel Library for LLM Serving
goliaro/moe_inference
goliaro/ms_thesis
goliaro/cmake_tutorial
A tutorial to become proficient in CMake
goliaro/cmu-catalyst.github.io
goliaro/codingInterview
coding interview brushup
goliaro/confluo
goliaro/cuda-toolkit
GitHub Action to install CUDA
goliaro/DAIL-SQL
A efficient and effective few-shot NL2SQL method on GPT-4.
goliaro/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
goliaro/FasterMoE
goliaro/fastermoe-ae
goliaro/FasterTransformer
Transformer related optimization, including BERT, GPT
goliaro/fastmoe
A fast MoE impl for PyTorch
goliaro/files
goliaro/FlexFlow
A distributed deep learning framework that supports flexible parallelization strategies.
goliaro/flexflow_huggingface
goliaro/GAN_PID
PID controller for GAN
goliaro/m2r2
Markdown to reStructuredText converter
goliaro/msquic
Cross-platform, C implementation of the IETF QUIC protocol.
goliaro/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
goliaro/netplay
goliaro/PyGithub
Typed interactions with the GitHub API v3
goliaro/ray
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
goliaro/rtd-tutorial
goliaro/test
goliaro/ubuntu-sysutils
goliaro/workflow_test
testing self-hosted machine for FlexFlow