4 points | by marcobambini 4 hours ago ago
2 comments
Current speed is “approximately one third of a token per second”
Right, we trade speed for the ability to run a 2.7T-parameter model while preserving accuracy. It is a first version, and we plan to improve the inference performance.
Current speed is “approximately one third of a token per second”
Right, we trade speed for the ability to run a 2.7T-parameter model while preserving accuracy. It is a first version, and we plan to improve the inference performance.