HN Explorer

somnial

↗ HN profile [ 83.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. What happens when a GPU writes memory (blog.doubleword.ai)
    3 points 0
  2. What happens when a GPU reads memory? (blog.doubleword.ai)
    15 points 0
  3. The case for disaggregated LLM serving (blog.doubleword.ai)
    4 points 0
  4. On-the-fly snapshot compression for elastic inference at scale (blog.doubleword.ai)
    6 points 1
  5. NVLink, NVSwitch, and All That (blog.doubleword.ai)
    5 points 2
  6. The Anatomy of an Instruction Pipeline Hazard (hiraditya.github.io)
    9 points 0
  7. Width vs. Depth: Speculating on the Margin (blog.doubleword.ai)
    17 points 1
  8. Pushing memory bound CUDA kernels past the speed of light with data compression (fergusfinn.com)
    2 points 0
  9. Speculative KV coding: ~4× losslessly compressed KV cache using a small model (fergusfinn.com)
    2 points 0
  10. 1 points 0
  11. 70x faster cold(ish) starts for SGLang (fergusfinn.com)
    1 points 0
  12. LLM powered data structures: A lock-free binary search tree (fergusfinn.com)
    1 points 0
  13. Parallel Primitives for Multi-Agent Workflows (fergusfinn.com)
    1 points 0
  14. Scheduling in LLM Inference (fergusfinn.com)
    1 points 0
  15. How fast can an LLM go? (fergusfinn.com)
    2 points 0