event

DeepSeek V4 Release

4 items · started 2026-11-11 · closed 2026-11-16

  1. DeepSeek V4 Pro 0813: Release Intelligence, Performance & Price Available providers Model summary Verbosity The DeepSeek V4 Pro 0813 release offers 3 models, each with different intelligence, performance, and pricing characteristics. Below…

  2. I'm completely new to orchestration, so I don't really know where to start. Could someone guide me through the process from scratch, starting with the basics?

  3. Reusing key--value (KV) caches across language model updates could avoid repeated computation of shared context, but changes in model weights raise a fundamental question about what these caches preserve. We investigate direct cache reuse…

  4. Our TWX3 build of DeepSeek-V4-Pro is 24% smaller than the model as published, within half a point of it on MMLU, and level on tool calls and made-up facts.

← all threads