arXiv:2405.04532 — QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

arXiv:2405.04532. v1 submitted 2024-05-07. Title on the /abs/ page confirmed as: "QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving". Venue/year for the corresponding paper record come from the Semantic Scholar graph API; see that record's notes where the arXiv comment field or OpenReview was used instead.