A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–10 of 10 · Most stars
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Nano vLLM
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
- calibration
- decision-model
- jev
- jev-model
Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
Native vLLM serving for Jev decision models
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)