zinccat's submissions

1.		Mooncake: A KVCache-Centric Disaggregated Architecture for LLM Serving (github.com/kvcache-ai)
		13 points by zinccat 5 days ago \| past \| discuss
2.		Best Papers at CVPR 2024 (fxguide.com)
		1 point by zinccat 14 days ago \| past
3.		Llama3V is suspected to have been stolen from the MiniCPM-Llama3-v2.5 project (github.com/openbmb)
		30 points by zinccat 31 days ago \| past \| 7 comments
4.		Generative AI in Search: Let Google do the searching for you (blog.google)
		6 points by zinccat 50 days ago \| past
5.		DeepSeek V2, near GPT4 performance with 30% GPT3.5 cost ($0.14M input tokens) (deepseek.com)
		16 points by zinccat 57 days ago \| past \| 2 comments
6.		SEQUOIA: Exact Llama2-70B on an RTX4090 with half-second per-token latency (infini-ai-lab.github.io)
		131 points by zinccat 60 days ago \| past \| 61 comments