DeepSeek V4.1 Flash: even the sparse indexer is itself sparse, with hierarchical candidate selection
nrehiew_ · x · 2026-09-11
nrehiew adds a detail on DeepSeek V4.1 Flash: the indexer itself is sparse. The first full-mode indexer selects candidates, which are then used for scoring in later layers — a hierarchical selection structure.
Related event: DeepSeek V4.1 Flash Deep Dive: KV Cache Compression at the Frontier(9 posts)→
More from Models
- Business Insider Asked ChatGPT, Gemini, Claude and Grok How AI Could End Humanity — coinfanking · 2026-09-11
- Claims resurface that Moonshot's Kimi distilled from Claude raw CoTs — xuanalogue · 2026-09-11
- User switches back to GPT-5.6 Sol: barely uses quota and feels faster — CtrlAltDwayne · 2026-09-11
- Dev opinion: model differences shrink in a good harness; Grok 4.6 is good enough — gnukeith · 2026-09-11
- DeepSeek-V4.1-Flash hits Ollama: 552B MoE backbone with 1M context via KV cache compression — ollama · 2026-09-11
- Ex-Meta threat chief praises Anthropic's most detailed AI misuse report — typewriters · 2026-09-11