ZSL98/openhands-aci
Agent computer interface for AI software engineer.
www.shulai.org
Repositories
ZSL98/zsl98.github.io
Shulai Zhang's Homepage
ZSL98/opencode
The open source coding agent.
ZSL98/claude-mem
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
ZSL98/agent_workspace
ZSL98/verl
veRL: Volcano Engine Reinforcement Learning for LLM
ZSL98/SkyRL-OpenHands
ZSL98/checkpoint-engine-ascend
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
ZSL98/mini-swe-agent
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
ZSL98/Megatron-LM
Ongoing research training transformer models at scale
ZSL98/study-demo
A collection of hands-on demos and code snippets for learning and experimenting with various programming concepts, frameworks, and tools. Ideal for self-study and quick references.
ZSL98/flux
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
ZSL98/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
ZSL98/FastEmbodiedAI
Fast Embodied AI
ZSL98/diffusion_policy
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
ZSL98/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
ZSL98/x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers
ZSL98/fastmoe
A fast MoE impl for PyTorch
ZSL98/tutel
Tutel MoE: An Optimized Mixture-of-Experts Implementation
ZSL98/CuAssembler
An unofficial cuda assembler, for all generations of SASS, hopefully ：）
ZSL98/benchmarks
ZSL98/TGS
Artifacts for our NSDI'23 paper TGS
ZSL98/orion
An interference-aware scheduler for fine-grained GPU sharing
ZSL98/PAME
Early Exits of DNN Networks with TensorRT
ZSL98/ccf-deadlines
⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~
ZSL98/nvsci
Linux kernel modules for secure sharing of memory buffers
ZSL98/cuda_hook
Hooked CUDA-related dynamic libraries by using automated code generation tools.
ZSL98/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
ZSL98/gdev_new
First-Class GPU Resource Management: Device Drivers, Runtimes, and CUDA Compilers for Nouveau.
ZSL98/gdev
First-Class GPU Resource Management: Device Drivers, Runtimes, and CUDA Compilers for Nouveau.