8000 llsj14 (Sungjae Lee) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View llsj14's full-sized avatar

Block or report llsj14

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Go 6,256 1,803 Updated Nov 21, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 24,305 4,941 Updated Nov 20, 2026

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Python 21,914 2,680 Updated Nov 20, 2026

Easier, quicker command-line CUDA profiling

Shell 71 7 Updated Sep 17, 2024

NVIDIA curated collection of educational resources related to general purpose GPU programming.

Jupyter Notebook 2,241 377 Updated Nov 19, 2026

An agentic context evolution approach for RTL coding

Python 50 12 Updated Sep 20, 2026

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost…

Rust 3,664 380 Updated Nov 21, 2026

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python 76,174 9,384 Updated Nov 21, 2026

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Python 147,984 17,625 Updated Nov 22, 2026

Nano vLLM

Python 16,524 2,879 Updated Apr 26, 2026

PersonaPlex on Apple Silicon: an MLX port of NVIDIA’s full-duplex speech-to-speech model with realtime local/web modes and offline WAV inference.

Python 91 19 Updated Feb 18, 2026

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Python 1,357 137 Updated Jul 8, 2026

End-to-end benchmark for AI-generated GPU kernels, drawn from real production traces — turn a PyTorch reference into a DSL kernel (Triton, Gluon, FlyDSL, CuteDSL) and grade it on compilation, numer…

Python 40 14 Updated Nov 10, 2026

An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU ke…

Python 217 41 Updated Nov 20, 2026

GPU kernel optimization framework

Python 40 2 Updated Oct 26, 2026

A unified inference runtime for VLA models.

C++ 274 55 Updated Nov 21, 2026

TokenSpeed is a speed-of-light LLM inference engine.

Python 2,944 424 Updated Nov 22, 2026

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing,…

Rust 736 230 Updated Nov 22, 2026

AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

Python 1,306 170 Updated Nov 19, 2026

A safetensors extension to efficiently store sparse quantized tensors on disk

Python 337 152 Updated Nov 19, 2026

Flash Vision-Language-Action Inference for Autonomous Driving

Python 101 10 Updated Sep 15, 2026

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Rust 87,424 5,612 Updated Nov 21, 2026

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Python 33,501 4,769 Updated Nov 22, 2026

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Python 12,408 2,176 Updated Nov 21, 2026

DSPy: The framework for programming—not prompting—language models

Python 39,169 3,536 Updated Nov 21, 2026

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Python 19,554 1,564 Updated Nov 19, 2026

Common recipes to run vLLM

JavaScript 1,095 503 Updated Nov 22, 2026

Offline optimization of your disaggregated Dynamo graph

Python 469 175 Updated Oct 29, 2026

A Datacenter Scale Distributed Inference Serving Framework

Rust 8,543 1,887 Updated Nov 22, 2026
Next
0