P
philipkiely
Article URL: How we run GPT OSS 120B at 500+ tokens per second on NVIDIA GPUs | Baseten Blog
Comments URL: Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs | Hacker News
Points: 142
# Comments: 55
Continue reading...
Comments URL: Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs | Hacker News
Points: 142
# Comments: 55
Continue reading...