gty111 / gLLM Star 66 Code Issues Pull requests Discussions An Efficient and Versatile Inference Engine for Distributed LLM Serving pipeline-parallelism tensor-parallelism llm-serving llm-inference pagedattention continuous-batching qwen3 token-throttling chunked-prefill Updated Jul 5, 2026 Python
CarolBaggins2023 / baby-vllm Star 4 Code Issues Pull requests A lightweight, educational LLM inference engine for studying continuous batching, paged KV cache, chunked prefill, and online serving. llm-serving llm-inference continuous-batching chunked-prefill paged-kv-cache Updated Jun 20, 2026 Python
wzqhbustb / qw3 Star 0 Code Issues Pull requests A minimal, native Metal inference engine for Qwen3-30B-A3B on Apple Silicon Macs. c macos metal objective-c transformer moe quantization inference-engine apple-silicon local-llm llm-inference gguf qwen3 chunked-prefill metal-kernels Updated Jul 2, 2026 C