How does varying the hot neuron activation threshold in PowerInfer impact Pass@1 scores on the HumanEval bench
Description
This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference, characterized by a power-law distribution in neuron activation. This distribution indicates that a small subset of neurons, termed hot neurons, are consistently activated across inputs, while the majority, cold neurons, vary based on specific inputs. PowerInfer exploits such an insight to design a GPU-CPU hybrid inference e
Research goal: How does varying the hot neuron activation threshold in PowerInfer impact Pass@1 scores on the HumanEval benchmark for LLaMA-33B compared to LLaMA-70B?
Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.
Notes
Files
paper.pdf
Files
(77.4 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:de39b7b58da3f72bbd9c78424b68ecca
|
77.4 kB | Preview Download |