GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz
(news.ycombinator.com)
1.
2.
3.
Can I Buy Your KV Cache?
(news.ycombinator.com)
4.
Exif Smuggling (2025)
(news.ycombinator.com)
5.
Exif Smuggling
(news.ycombinator.com)
6.
Speculative KV coding: losslessly compressing KV cache by up to ~4×
(news.ycombinator.com)
7.
KVarN: Native vLLM backend for KV-cache quantization by Huawei
(news.ycombinator.com)
8.
KVarN: Native vLLM KV-cache quantization back end by Huawei
(news.ycombinator.com)
9.
Microsoft blames unexpected Windows driver updates on caching issue
(bleepingcomputer.com)
10.
Users say Gemini starts forgetting long before it’s supposed to
(androidauthority.com)
11.
Every Byte Matters
(news.ycombinator.com)
12.
Social Cache Busting
(news.ycombinator.com)
13.
14.
AMD extends Socket AM5 support through at least 2029; AM4 refuses to die
(arstechnica.com)
15.
16.
17.
18.
How can your company show up during Pride Month?
(feeds.feedburner.com)
19.
DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
(news.ycombinator.com)
20.
Developers: Get Your Medical Mobile App Verified By IEEE
(spectrum.ieee.org)
21.
Throwing AI-generated walls of text into conversations
(news.ycombinator.com)
22.
Stop throwing AI-generated walls of text into conversations
(news.ycombinator.com)
23.
No Slop Grenade
(news.ycombinator.com)
24.
27.
Autoregressive next token prediction and KV Cache in transformers
(news.ycombinator.com)
28.
KV Cache Is Becoming the Memory Hierarchy of Inference
(news.ycombinator.com)
29.
Understanding Singleflight in Go
(news.ycombinator.com)
30.
The Third Hard Problem
(news.ycombinator.com)