AI-Wiki

Tag: deepseek-r1

2 items with this tag.

  • Aug 30, 2026

    Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets

    • multi-agent
    • single-agent
    • token-budget
    • data-processing-inequality
    • information-efficiency
    • multi-hop-reasoning
    • qwen3
    • deepseek-r1
    • gemini-2-5
    • test-time-compute
    • confounding
    • type/source
    • kind/paper
  • May 13, 2026

    How LLMs survive in low precision | Quantization Fundamentals

    • quantization
    • model-compression
    • inference-optimization
    • ptq
    • qat
    • fixed-point-arithmetic
    • bfloat16
    • deepseek-r1
    • llama-4
    • h100
    • coral-edge-tpu
    • ggml
    • gguf
    • gptq
    • awq
    • unsloth
    • qwen
    • julia-turc
    • edge-ml
    • one-bit-llm
    • calibration
    • clipping-range
    • zero-point
    • ieee-754
    • type/source
    • kind/video

Created with Quartz v0.1.0 © 2026

254 sources · 171 entities · 47 concepts · 7 threads · 5 syntheses

  • GitHub