GitHub Hot Board · Hồ sơ kho lưu trữ

syv-ai/HyperQwen

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. (Mô tả đến từ chính kho lưu trữ.)

Dữ liệu tại October 22syv-ai