cuda

GPU-accelerated javascript runtime for StableDiffusion. Uses modified ONNX runtime to support CUDA and DirectML.

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cloning, and 23 languages.

DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.

Generate textured, segmented and rigged GLB assets entirely on your own GPU.

This repository lists some awesome public Rust projects, Videos, Blogs and Jobs.

Bleeding edge vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a).

A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

useful Gentoo overlay Curated ebuilds, AI, tools & science

Native Windows vLLM 0.27.1 wheels: Python 3.13, PyTorch 2.13 + CUDA 13.0, SM 7.5-12.0 for RTX 20/30/40/50, OpenAI-compatible serving, FlashAttention/Rust, 10 KV formats, Multi-TurboQuant, and experimental CPU/RAM/NVMe prompt-KV offload - no WSL or Docker.

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, TUI, iPhone, REST/SSE, and MCP.

From-scratch C++23/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a). The best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents. Decode beats llama.cpp b9976 by 42-48% on dense GGUF (measured 2026-07-12), at-or-ahead of vLLM on NVFP4. 100% written by Claude Code.

GPU 性能与 AI Infra 学习项目：CUDA/Triton 算子、NCU/NSYS、vLLM/SGLang/TRT-LLM/ms-swift、PyTorch/DeepSpeed/ms-swift 训练、并行架构

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable cards.

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

A "standard library" of Triton kernels.

Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on top of SystemPanic 0.19.0. Engine for devnen/qwen3.6-windows-server.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualification, CUDA weight sharing, and multi-GPU planning.

🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models.

Serve Poolside Laguna S 2.1 (NVFP4) on the NVIDIA DGX Spark (GB10) without hanging your box. Working stack, crash-safe configs, benchmarks, and the exact gotchas.