Chengyuan Li

Results 3 issues of Chengyuan Li

I have 3 questions about DCGM, I noticed that there are field identifiers like memory utilization and gpu utilization. 1. How these methods are calculated? 2. What if I want...

question

As mentioned [here](https://github.com/SafeAILab/EAGLE/issues/31#issuecomment-1927696940), any updates? Btw, the [checkpoint](https://huggingface.co/yuhuili/EAGLE-mixtral-instruct-8x7B) you released on huggingface is also just one transformer layer, right?

In GQA, only one copy of kv cache will be saved for each group, but snapKV saves kv cache with `num_key_value_heads * num_key_value_groups` heads. Indeed in kv cache eviction, the...