Hackernews posts about Llama 3.1 405B

1. Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (cerebras.ai)
   427 points by benchmarkist almost 2 years ago | 156 comments
2. HuggingFace - Tencent launches Hunyuan Large which outperforms Llama 3.1 405B (huggingface.co)
   23 points by janik-io almost 2 years ago | 1 comments
3. Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs (dstack.ai)
   11 points by latchkey almost 2 years ago | 3 comments
4. The Future of AI: Synthetic Data Gen with Llama 3.1 405B and Raft (techcommunity.microsoft.com)
   6 points by mfiguiere almost 2 years ago | 1 comments
5. Create a free Llama 3.1 405B-powered chatbot on a GitHub repo in <1 min (blog.stephenturner.us)
   2 points by turnersd almost 2 years ago | discuss
6. How to Run Meta Llama 3.1 405B with Nebius AI Studio API (nebius.com)
   1 points by dsaed almost 2 years ago | discuss
7. We fine-tuned Llama 405B on AMD GPUs (publish.obsidian.md)
   495 points by felarof almost 2 years ago | 101 comments
8. Discuss HN: Will 100M token LLMs replace most programmers?
   3 points by Mariciano almost 2 years ago | 6 comments
9. Show HN: How to guide on training Llama-405B using PyTorch distributed APIs (github.com)
   3 points by lambda-research almost 2 years ago | 4 comments
10. Ask HN: AI Cloud Computing, is it cheaper than the OpenAI API in the end?
    2 points by calipsow almost 2 years ago | 4 comments
11. Vakgpt: Open-Source Chat Wrapper for Rapid AI Prototyping
    1 points by krishna-vakx about 1 year ago | discuss
12. AllenAI Tulu 3 405B available for chat and download
    12 points by soundworlds over 1 year ago | discuss
13. Show HN: Slash your LLM Inference Costs with Overnight Processing
    5 points by Blue_Cosma almost 2 years ago | 1 comments
14. Show HN: Slashing LLM Costs for Overnight Batch Inference
    2 points by Blue_Cosma almost 2 years ago | discuss
15. Show HN: Most Efficient Batch API for Open-Source and Custom Models (withexxa.com)
    1 points by Blue_Cosma almost 2 years ago | discuss