HN Explorer

OsamaJaber

↗ HN profile [ 61.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. The AGI Compiler "Auto" (github.com)
    1 points 0
  2. Compiler for LLMs, world models, and AGI (arxiv.org)
    1 points 0
  3. Auto: The AGI Compiler (github.com)
    2 points 2
  4. Build You Own Model (runinfra.ai)
    2 points 0
  5. RunInfra: Optimize any open model down to the kernel, deploy in 5 min (runinfra.ai)
    2 points 0
  6. Compiles any HuggingFace model into a single persistent megakernel (twitter.com)
    2 points 0
  7. Mega Kernels, Written by Agents (arxiv.org)
    2 points 0
  8. AutoMegaKernel: Compiling a LLM into a single CUDA kernel (arxiv.org)
    3 points 0
  9. AutoMegaKernel: Compile an LLM into one provably-correct CUDA megakernel (github.com)
    4 points 1
  10. StreamIndex: Memory-bounded compressed sparse attention via streaming top-k (arxiv.org)
    4 points 0
  11. Show HN: AutoKernel, Auto GPU Kernel Optimization (arxiv.org)
    2 points 0
  12. DeepSeek V4's indexer dies at 65K. We got it to 1M on 6GB (arxiv.org)
    5 points 0
  13. AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search (arxiv.org)
    4 points 0
  14. DeepSeek V4's indexer OOMs at 65K context. We got it to 1M in 6G (arxiv.org)
    8 points 0
  15. Ouroboros: Dynamic Weight Generation for Recursive Transformers (arxiv.org)
    2 points 0
  16. Tide: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference (arxiv.org)
    3 points 1
  17. Own your AI. Optimized down to the kernel (runinfra.ai)
    1 points 1
  18. 1 points 0
  19. 1 points 0
  20. Agents with "Hands" (openfang.sh)
    7 points 9
  21. Open-Source Agent Operating System (github.com)
    11 points 3
  22. PicoLM: Run a 1B parameter LLM on a $10 board (github.com)
    4 points 1
  23. 1 points 0
  24. The Floating Dock for Developers (snap-dock.co)
    2 points 0
  25. 1 points 0