HN Explorer

junrushao1994

↗ HN profile [ 83.6 ms ] full profile
Karma
237
Created
July 12, 2018 (8y ago)
Submissions
0
Junru Shao junrushao1994 at gmail.com Options are my own
  1. Scaling LLama2-70B with Multiple Nvidia/AMD GPU (blog.mlc.ai)
    13 points 6
  2. MLC LLM: 70B Llama-2-4bit on MacBook at 50%-80% speed of A100 (twitter.com)
    12 points 3
  3. Running RedPajama and other open LLMs on phones, browsers and AMD/NV/Intel GPUs (mlc.ai)
    11 points 0
  4. MLC: Bringing Hardware Accelerated Language Models to Consumer Devices (mlc.ai)
    8 points 0
  5. MLC-LLM: GPT/Llama on consumer-class GPUs and phones (github.com)
    303 points 106