DFlash 2: Keep Drafting Parallel

4 comments

• hypfer 1 hour ago
  Amazing tech

  > An agent writes in an afternoon what a chatbot writes in a month

  But can you just.. not.

  Your tech is so good, it speaks for itself. Don't ruin that.
• adefa 1 hour ago
  I'm getting around 27 tokens per second decode using vLLM + Qwen 3.8 27b nvfp4 + DFlash 2 on the DGX Spark.
• sarjann 1 hour ago
  Great news, has made low memory bandwidth model usage so much nicer.
• verdverm 2 hours ago
  vllm PR for DFlash2: https://github.com/vllm-project/vllm/pull/52816
  [-]
  • cogman10 1 hour ago
    llama.cpp PR https://github.com/ggml-org/llama.cpp/pull/27342