HN Explorer

kkm

↗ HN profile [ 82.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. The Agent swarm that designs itself (peterbhabra.com)
    1 points 0
  2. Don't Build a Router. Train the Small Model to Know When to Defer (distillabs.ai)
    2 points 1
  3. The gap between open weights LLMs and closed source LLMs (blog.doubleword.ai)
    304 points 30
  4. 1 points 0
  5. InfiniBand, RoCE, and All That (fergusfinn.com)
    5 points 0
  6. 2678x Faster Matrix Multiplication with a GPU (0mean1sigma.com)
    2 points 0
  7. UCCL-EP: DeepEP-style expert parallelism on any NIC, no GPU-initiated comms (fergusfinn.com)
    9 points 0
  8. Hacking Google with A.I. For $500k (brutecat.com)
    1 points 0
  9. How to setup a local coding agent on macOS (ikyle.me)
    507 points 57
  10. Anatomy of a high-performance EP kernel (fergusfinn.com)
    16 points 1
  11. No Token Left Behind: Demystifying Token-in-Token-Out in Miles (lmsys.org)
    2 points 0
  12. MoE expert co-activations: Reordering inputs yields easy throughput gains (blog.doubleword.ai)
    2 points 0
  13. The Economics of Speculative Decoding (fergusfinn.com)
    30 points 4
  14. Speculative KV coding: losslessly compressing KV cache by up to ~4× (fergusfinn.com)
    155 points 12
  15. 70x faster cold(ish) starts for SGLang (fergusfinn.com)
    1 points 0
  16. Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)
    120 points 11
  17. Brave AI privacy:LLMs on NEAR AI Nvidia-Backed Trusted Execution Environments (brave.com)
    1 points 0
  18. How fast can an LLM go? (fergusfinn.com)
    2 points 0
  19. FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner (huggingface.co)
    4 points 0
  20. Harnessing the Power of Large Language Models for Insightful Review Analysis (techblog.holidaycheck.com)
    1 points 0
  21. A Privacy-First approach to use AI for understanding our Customers Better (techblog.holidaycheck.com)
    1 points 0
  22. How to make LLMs go fast (vgel.me)
    2 points 0
  23. Leveraging Large Language Models for Sentiment Classification in Hotel Reviews (techblog.holidaycheck.com)
    1 points 0
  24. 1 points 0
  25. Managers Should Think More Like Hackers (hbr.org)
    3 points 0