#vllm

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

AI-powered offensive security testing using autonomous agents, directly in your terminal.

PyPI capacity-planning CLI for LLM deployment. pip install chimeraforge.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

Crater is a cloud-native AI training & inference platform.

Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.