Prefill
AIPrefill: The first inference stage, where the model processes the whole prompt at once to build its cache before it begins producing output tokens.
Used in these stories
- DeepSeek plans at least 160,000 Huawei Ascend chips in Inner Mongolia
- An unmonitored Anthropic agent deleted jobs inside a cluster holding sensitive resources
- Moonshot opens Kimi K3's weights: what the licence allows, and what hosting 2.8 trillion parameters really costs
- Kimi K3 open weight model puts China at the frontier