NemoClaw Knowledge Wiki

Tag: speculativedecoding

5 items with this tag.

  • Jul 04, 2026

    DeepSeek DFlash Accelerates Gemma 12B LLM Text Generation up to 5x

    • deepseek
    • dspark
    • mtp
    • speculativedecoding
    • dflash
  • Jun 30, 2026

    DeepSpec DSparK: Local Qwen3 LLM Acceleration through Speculative Decoding

    • deepseek
    • dspark
    • mtp
    • speculativedecoding
  • Jun 29, 2026

    DeepSeek DSpark: Optimizing Speculative Decoding for Accelerated LLM Inference

    • dspark
    • deepseek
    • speculativedecoding
  • Jun 03, 2026

    Adaptive PFlash and Hermes Agent: Self-Tuning LLM Prefill for Long Contexts

    • llamacpp
    • lucebox
    • lucedflash
    • speculativedecoding
    • pflash
  • May 20, 2026

    MTP + Ngram Stacked Speculative Decoding in Llama.cpp for LLM Inference

    • llamacpp
    • mtp
    • multitokenprediction
    • speculativedecoding
    • ngrammod

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community