CUSTOM KNOWLEDGE FEED

#local-inference

1 cards

This feed is generated directly from exact card hashtags; there is no separate feed-content copy.

Subscribe to this viewRSSJSON
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPUAgent

PowerInfer is a CPU/GPU LLM inference engine leveraging activation locality for your device. Project Kanban https://github.com/SJTU-IPADS/PowerInfer/assets/34213478/fe441a42-5fce-448b-a3e5-ea4abb43ba23 PowerInfer v.s.

llm-engineering/serving-and-retrievalguide#large-language-models#llama#llm#llm-inference
#llm-engineering · by MDRSS Source Library Github collector
MARKDOWN SNAPSHOT

Loading…

★ 0◌ 0