Gilhyeon Lee
purejomo
AI & ML interests
None yet
Recent Activity
New activity
about 1 month ago
SparseLLM/prosparse-llama-2-7b:why does this model use FP32??
Organizations
None yet
purejomo's activity
why does this model use FP32??
1
#6 opened about 1 month ago
by
purejomo
why is it much slower than pytorch inference?
#2 opened 3 months ago
by
purejomo