Replies: 1 comment
-
|
Hey @gmerritt, we are indeed well aware of this new paper, thanks for pinging us! 👍 We are currently working on updating our benchmarking data with new optimized methods (quantization, batching, vllm, etc.) and new hardware. Section 4.3 of this paper contains a list of optimization methods that should explain the majority of the x33 diminishing factor in energy in one year: so we can indeed leverage this list for our new benchmark (and therefore improve the methodology, even for other models that Gemini). |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Can this newly-released information from Google be leveraged to improve ecologits estimates for Gemini models?
https://cloud.google.com/blog/products/infrastructure/measuring-the-environmental-impact-of-ai-inference/
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions