issues
search
microsoft
/
vattention
Dynamic Memory Management for Serving LLMs without PagedAttention
MIT License
185
stars
11
forks
source link
Update scripts and fix avoidable exceptions
#10
Closed
apanwariisc
closed
1 month ago
apanwariisc
commented
1 month ago
Round up the size of virtual memory allocation to prevent avoidable exceptions
Minor updates to benchmarking scripts