-
AWS
- Beijing, China
- https://www.linkedin.com/in/henanwang
Stars
- All languages
- AGS Script
- C
- C#
- C++
- CMake
- CSS
- CoffeeScript
- Cuda
- Cython
- Dockerfile
- GLSL
- Go
- Graphviz (DOT)
- HTML
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MATLAB
- MDX
- MLIR
- Markdown
- Objective-C
- Objective-C++
- OpenSCAD
- PHP
- PLpgSQL
- Perl
- PowerShell
- Protocol Buffer
- Pug
- PureBasic
- Python
- R
- Ruby
- Rust
- Scala
- Shell
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- Vim Script
- Vue
gregnetau / vllm-neuron
Forked from vllm-project/vllm-neuronCommunity maintained hardware plugin for vLLM on AWS Neuron
An LLM inference engine for AWS Trainium: the serving techniques of vLLM and SGLang, rebuilt for ahead-of-time compiled graphs
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
A flexible distributed key-value database that is optimized for caching and other realtime workloads.
A valkey module intended for performant storage and transfers of large sized objects
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
TPUMS (TPU Microbenchmark Suite) is a modular, high-fidelity benchmarking and profiling framework designed to evaluate the compute, memory, and interconnect performance of Cloud TPUs using JAX.
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSim), and more.
mKernel: fast multi-node, multi-GPU fused kernels
htop-like TUI for real-time RDMA network monitoring.
A lightweight library for xPU kernel JIT compilation
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
vLLM Omni backend plugin for diffusion and multimodal generation on AWS Trainium
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
Ideogram 4: Open image model at the forefront of design
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Agent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-level voiceover sync, 109 motion recipe cards, an anti-slideshow camera system, R…
Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar…
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.
Lightweight Image Video Action Generation Inference Framework
VideoDeltaNet-H3: Live T2VA / I2VA / FL2VA / Ref2VA-like generation based on Minimax H3.