Popular repositories Loading

1. prompt-guard-2-frozen-head prompt-guard-2-frozen-head Public

   Phase-5 injection-classifier pipeline: A calibrated linear head trained on Prompt Guard 2 frozen embeddings achieving 99.9% OOD recall.

   TeX 8

2. TokenFlow-Gateway TokenFlow-Gateway Public

   TokenFlow is an enterprise-grade, token-aware load balancer and AI gateway for vLLM. It prevents GPU OOM crashes using Redis-backed admission control, semantic caching, and dynamic token routing. B…

   TypeScript 8

3. accelerate accelerate Public

   Forked from huggingface/accelerate

   🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

   Python 4

4. sglang sglang Public

   Forked from sgl-project/sglang

   SGLang is a high-performance serving framework for large language models and multimodal models.

   Python 4

5. AI-Powered-Itinerary-Generator AI-Powered-Itinerary-Generator Public

   A serverless application built with Cloudflare Workers that generates personalized travel itineraries using AI and stores them in Firestore. The API responds instantly with a tracking ID while gene…

   JavaScript

6. AI-Itinerary-Status-Checker---Frontend AI-Itinerary-Status-Checker---Frontend Public

   A modern, real-time travel planning interface built with Svelte 5 that allows users to create AI-generated itineraries and track their status in real-time. Features dual functionality for both crea…

   Svelte