vLLM v0.28.0 released: major performance gains for Kimi-K3 and DeepSeek V4
A high-throughput and memory-efficient inference and serving engine for LLMs - Release v0.28.0 · vllm-project/vllm
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open github.com original