ByronHsu/Never-Blink
👀Blink and lose.
RL System at Periodic Labs | SGLang, ex-xAI
Repositories
ByronHsu/life-commit
🏃📆 Life as a git. Commit on your life.
ByronHsu/byronhsu.github.io
Notes, demos, benchmarks, and other things I publish.
ByronHsu/sgl-router-for-miles
The sglang router for miles only.
ByronHsu/Computer_Architecture
108-1 NTUEE CA program assignment
ByronHsu/k3-inference-calculator
Interactive theoretical Kimi-K3 inference roofline calculator for H200, B300, and GB300
ByronHsu/smoe-debug
Enhancing ScatterMoE
ByronHsu/miles
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
ByronHsu/FEGAN
Self-Supervised Deep Learning for Fisheye Image Rectification (pytorch implementation).
ByronHsu/rust-ibverbs
Bindings for RDMA ibverbs through rdma-core
ByronHsu/FlyteGPT
🦅🔗 Building FlyteGPT on Flyte with LangChain
ByronHsu/FRAIGs
C++ implementation of FRAIGs. Won the 1st place in 2018 Cadence-sponsored contest in NTU DSnP.
ByronHsu/AAG-Visualizer
🌆 🏙 🌃 Viz.js Graphviz - An Elegant Visualizer for And-Inverter Graph
ByronHsu/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
ByronHsu/ao
PyTorch native quantization and sparsity for training and inference
ByronHsu/SGEMM_CUDA
Fast CUDA matrix multiplication from scratch
ByronHsu/java-fullstack-practice
Follow the steps-by-steps tutorial on Udemy course - "Java - ambitious start. Create a real web app!" to build a mini project
ByronHsu/submarine
Submarine is Cloud Native Machine Learning Platform.
ByronHsu/flashinfer
FlashInfer: Kernel Library for LLM Serving
ByronHsu/PYNote
Learning python
ByronHsu/sglang-rust-test
ByronHsu/trl
Train transformer language models with reinforcement learning.
ByronHsu/sgl-learning-materials
Materials for learning SGLang
ByronHsu/lightning-thunder
Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.
ByronHsu/sglang
SGLang is a fast serving framework for large language models and vision language models.
ByronHsu/flux
Official inference repo for FLUX.1 models
ByronHsu/triton
Development repository for the Triton language and compiler
ByronHsu/lectures
Material for cuda-mode lectures
ByronHsu/LLaMA-Factory
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
ByronHsu/axolotl
Go ahead and axolotl questions