Tag

Language Model Evaluation Harness

Unified framework for few-shot evaluation of generative language models across 60+ academic benchmarks. Supports multiple model backends (Hugging Face, vLLM, APIs, local servers), configurable prompts/YAML configs, and reproducible exports for leaderboards and research comparisons.

KServe

Serves predictive and generative ML models on Kubernetes via a single InferenceService CRD, with scale-to-zero, canary rollouts, and an OpenAI-compatible LLM path on vLLM. One autoscaling abstraction over PyTorch, XGBoost, ONNX, and HuggingFace.

vLLM

Open-source LLM inference and serving engine built around PagedAttention, which manages the KV cache like OS virtual memory to cut waste and raise throughput. Supports continuous batching, KV cache sharing, quantization, and an OpenAI-compatible API.

LocalAI

Puts OpenAI-, Anthropic- and Ollama-compatible endpoints in front of 60+ inference backends, so existing client code runs unchanged against local models for text, vision, audio, image and embeddings. Runs CPU-only or accelerated, data stays local.

LLaMA-Factory

Fine-tunes 100+ LLMs and VLMs from one config file or a no-code web UI, unifying LoRA, QLoRA, full tuning, DPO, PPO, KTO and ORPO behind a single interface. Bundles GaLore, Unsloth, FlashAttention-2 and 2-8bit quantization to fit a single 24GB GPU.

Xorbits Inference (Xinference)

Run any open-source LLM, embedding, speech, image, or multimodal model behind one OpenAI-compatible API — swap GPT for an open model in a single line. Routes across vLLM, llama.cpp, GGML, and TensorRT, scaling from a laptop to a multi-node GPU cluster.

OpenRLHF

Trains LLMs with RLHF at scale by splitting actor, critic, reward, and reference models across separate GPU groups via Ray, with vLLM-accelerated generation and DeepSpeed ZeRO-3. Supports PPO, GRPO, REINFORCE++, DPO, plus async and agentic multi-turn RL.

LitServe | Deploy any AI model Lightning fast

Builds custom AI inference servers in pure Python on top of FastAPI, keeping full control over request logic while batching, GPU autoscaling, streaming, and OpenAI-spec endpoints come built in. Claims a 2x+ throughput edge over plain FastAPI.

Surya

Performs document OCR, layout analysis, reading-order detection and table recognition across 90+ languages using a ~650M-parameter vision–language model; offers per-page and per-block modes and supports GPU (vllm) and CPU/Apple Silicon backends.

MiniCPM-V

Pocket-sized multimodal LLM for efficient image- and video-understanding on mobile and edge devices, featuring mixed 4x/16x visual-token compression (MiniCPM‑V 4.6), compact 1.3B variants, and ready guides for iOS/Android/HarmonyOS deployment.

FlashInfer

GPU kernel library for LLM inference attention, sampling, and KV-cache, built on block-sparse formats with JIT-compiled customizable templates. Reports 29-69% inter-token-latency cuts vs compiler backends; powers SGLang, vLLM, and MLC-Engine.

Oumi

Streamlines the full lifecycle of foundation models — data prep, fine-tuning (SFT/LoRA/QLoRA/GRPO), evaluation, and deployment — with ready-to-run recipes, multi-engine inference support, and cloud/CLI workflows for both laptop experiments and large-scale runs.