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.
Repository Index
47,133 repositories indexed
1–7 of 7 · Most stars
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.
🧱 Experimental library for building inference engines
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.