jd-opensource/xllm
**Brief Summary (2‑3 sentences)** jd‑opensource/xllm is a high‑performance inference engine written in C++ that supports large language models (LLM), vision‑lan
Original source**Brief Summary (2‑3 sentences)** jd‑opensource/xllm is a high‑performance inference engine written in C++ that supports large language models (LLM), vision‑lan
Original source