DeepSeek-V4 makes million-token context a serving-systems problem. Together AI explores the inference work behind V4 on NVIDIA HGX B200, including compressed KV layouts, prefix caching, kernel maturity, and endpoint profiles for long-context workloads.
Serving DeepSeek-V4: why million-token context is an inference systems problem
calendar_today
May 11, 2026
domain
together-ai