ByteDance Seed: with chunked KV-cache compression, open-weight models such as DeepSeek-V4 show long-context retrieval accuracy differing by up to 40 percentage points across “phases” — shifts of the input by a few tokens
translated by AI, reviewed by the editors
· Software development · Science
- technology
- Open weights
- source
- arxiv.org ↗
¶ ch6kngnju