kkm | Dark Hacker News

user:	kkm
created:	August 2, 2016
karma:	2.2k

1.	Guide to the Kimi DeltaNet Family of linear attention(blog.doubleword.ai) 3 points by kkm 35 days ago \| 0 comments
2.	Forensic Analysis of Container Snapshot Chains for Post-Event Reconstruction [pdf](radostin.io) 2 points by kkm 41 days ago \| 0 comments
3.	The Agent swarm that designs itself(peterbhabra.com) 1 points by kkm 62 days ago \| 0 comments
4.	Don't Build a Router. Train the Small Model to Know When to Defer(distillabs.ai) 2 points by kkm 62 days ago \| 1 comment
5.	The gap between open weights LLMs and closed source LLMs(blog.doubleword.ai) 306 points by kkm 66 days ago \| 250 comments
6.	1 points by kkm 70 days ago \| discuss
7.	InfiniBand, RoCE, and All That(fergusfinn.com) 5 points by kkm 73 days ago \| 0 comments
8.	2678x Faster Matrix Multiplication with a GPU(0mean1sigma.com) 2 points by kkm 76 days ago \| 0 comments
9.	UCCL-EP: DeepEP-style expert parallelism on any NIC, no GPU-initiated comms(fergusfinn.com) 9 points by kkm 77 days ago \| 0 comments
10.	Hacking Google with A.I. For $500k(brutecat.com) 1 points by kkm 80 days ago \| 0 comments
11.	How to setup a local coding agent on macOS(ikyle.me) 507 points by kkm 80 days ago \| 127 comments
12.	Anatomy of a high-performance EP kernel(fergusfinn.com) 16 points by kkm 82 days ago \| 1 comment
13.	No Token Left Behind: Demystifying Token-in-Token-Out in Miles(lmsys.org) 2 points by kkm 83 days ago \| 0 comments
14.	MoE expert co-activations: Reordering inputs yields easy throughput gains(blog.doubleword.ai) 2 points by kkm 84 days ago \| 0 comments
15.	The Economics of Speculative Decoding(fergusfinn.com) 30 points by kkm 84 days ago \| 6 comments
16.	Speculative KV coding: losslessly compressing KV cache by up to ~4×(fergusfinn.com) 155 points by kkm 88 days ago \| 48 comments
17.	70x faster cold(ish) starts for SGLang(fergusfinn.com) 1 points by kkm 89 days ago \| 0 comments
18.	Bringing Up DeepSeek-V4-Flash on AMD MI300X(fergusfinn.com) 120 points by kkm 90 days ago \| 25 comments
19.	Brave AI privacy:LLMs on NEAR AI Nvidia-Backed Trusted Execution Environments(brave.com) 1 points by kkm 284 days ago \| 0 comments
20.	How fast can an LLM go?(fergusfinn.com) 2 points by kkm 293 days ago \| 0 comments
21.	FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner(huggingface.co) 4 points by kkm 2 years ago \| 0 comments
22.	Harnessing the Power of Large Language Models for Insightful Review Analysis(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
23.	A Privacy-First approach to use AI for understanding our Customers Better(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
24.	How to make LLMs go fast(vgel.me) 2 points by kkm 2 years ago \| 0 comments
25.	Leveraging Large Language Models for Sentiment Classification in Hotel Reviews(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
26.	1 points by kkm 3 years ago \| discuss
27.	Managers Should Think More Like Hackers(hbr.org) 3 points by kkm 3 years ago \| 0 comments