Alex-Wengg/Alex-Wengg
Profile README
AI Researcher
Profile README
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
SGLang is a high-performance serving framework for large language models and multimodal models.
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
A programmable Mixture-of-Models router for heterogeneous LLM inference
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
HTTP client library built on SwiftNIO
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
A high-throughput and memory-efficient inference and serving engine for LLMs
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Kokoro TTS on CoreML — 25× real-time on M4 Mac Mini, 17× on iPhone 16 Pro, ANE-optimized 7-stage pipeline.
A meeting note-taker that talks back.
NeMo text processing for ASR and TTS
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
Largest list of models for Core ML (for iOS 11+)
Your personal AI guardian of knowledge - macOS app for document research with MLX
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
:fire: Learn some Swift
A List of Awesome Swift Playgrounds
Space Invader game replica in Pygame
coded in c++ from https://github.com/dyn4mik3/OrderBook
So this Terran bot can harvest minerals and vespene gas and build up a small army of marines and medivacs send to attack the enemy base.