llm-inference

Native Windows vLLM 0.27.1 wheels: Python 3.13, PyTorch 2.13 + CUDA 13.0, SM 7.5-12.0 for RTX 20/30/40/50, OpenAI-compatible serving, FlashAttention/Rust, 10 KV formats, Multi-TurboQuant, and experimental CPU/RAM/NVMe prompt-KV offload - no WSL or Docker.

Tree prompting: easy-to-use scikit-learn interface for improved prompting.

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

🔥 Alternative to Ollama — multi-model serving with sub-ms model switching · CPU-only 20B inference for Edge AI · llama.cpp + stablediffusion.cpp

Carbon Limiting Auto Tuning for Kubernetes

Fine-tune Mistral 7B to generate fashion style suggestions

From-scratch C++23/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a). The best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents. Decode beats llama.cpp b9976 by 42-48% on dense GGUF (measured 2026-07-12), at-or-ahead of vLLM on NVFP4. 100% written by Claude Code.

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/TTFT/KV cards. Point it at your own hardware.

The OllaLab-Lean project is designed to help both novice and experienced developers rapidly set up and begin working on LLM-based projects.

Distributed peer-to-peer LLM inference. Your prompt never leaves your device in clear text.

面向开发者与初学者的 nano-vLLM 交互式源码教程 - 通过 13 个 HTML 互动实验 + 13 章中文教程理解大模型推理引擎

Dockerized LLM inference server with constrained output (JSON mode), built on top of vLLM and outlines. Faster, cheaper and without rate limits. Compare the quality and latency to your current LLM API provider.

Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on top of SystemPanic 0.19.0. Engine for devnen/qwen3.6-windows-server.

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

Truthful scheduler-step and streaming visualization for local LLM inference

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

Kubernetes scanner that discovers LLMs running on vLLM and extracts their deployment and runtime facts.

An imperative command-line-interface for AI workload orchestration

大模型推理框架加速，让 LLM 飞起来

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.