HN Explorer

manili

↗ HN profile [ 44.6 ms ] full profile
Karma
2
Created
June 12, 2018 (8y ago)
Submissions
0
  1. How much does CoT Reasoning typically cost for frameworks like LlamaIndex?

    I'm curious to know, based on your experience in production, how much does Chain-of-Though Reasoning typically cost in terms of tokens for frameworks like LlamaIndex, LangChain, CrewAI, etc.? I understand it depends on…

    2 points 4
  2. Ask HN: The Cost of Building an AI Workflow with Open-Source Tools for a Startup

    Hi everyone, I'm planning to build an AI workflow using open-source tools like models, vector databases, and frameworks (e.g., crewAI, langchain, llamaindex) without doing any training or fine-tuning. Can anyone share…

    1 points 1
  3. Ask HN: Privacy-Aware Inferencing for LLMs

    Hello, One of the biggest challenges with cloud-based inferencing for LLMs is keeping user data private. Is it possible to use both local and cloud machines together to solve this? For example, could we run the first…

    1 points 2
  4. Ask HN: Versal HBM Series vs. Nvidia A100 for LLM Training?

    Hello all, I am very curious to know how feasible it is to use a cluster of Versal HBM Series (e.g. VHK158 evaluation board) for training an LLM like LLaMA-2 70B in terms of 'Performance/Power/Cost.' Are there any…

    2 points 2
  5. Versal HBM Series vs. Nvidia A100 for LLM Training?

    Hello all, I am very curious to know how feasible it is to use a cluster of Versal HBM Series (e.g. VHK158 evaluation board) for training an LLM like LLaMA-2 70B in terms of 'Performance/Power/Cost.' Are there any…

    1 points 0
  6. Ask HN: Designing New RPi for Doing HPC, ML, etc.?

    Hi guys, I saw lots of people clustered their RPis for different purposes (e.g. data mining, machine learning, big data storage and Hadoop and so on ...). As you know RPi has it's own drawbacks. For example lack of…

    2 points 5