Trade Whisperer(@TradexWhisperer):Inference becomes 70 to 90% of all AI compute by 2030, and KV cache is its single biggest memory consumer. $MU has solutions for all levels of KV cache to enable Contextual Intelligence: HBM > DDR5 > disaggregated DRAM > NVMe

Trade Whisperer

@TradexWhisperer

Published $MU Bargain Thesis at $62. $PLTR $21. $RKLB $10. $SNDK $214. Memory Engineer. Data Scientist. Founder of Blue Pink Candles. Masters 🎓 @UofIllinois

加入 February 2012

153 正在关注 144.2K 粉丝

Trade Whisperer@TradexWhisperer

2026.09.18 04:56

Inference becomes 70 to 90% of all AI compute by 2030, and KV cache is its single biggest memory consumer. $MU has solutions for all levels of KV cache to enable Contextual Intelligence: HBM > DDR5 > disaggregated DRAM > NVMe > data lakes. Every tier is theirs.

显示更多