issues
search
ankan-ban
/
llama2.cu
Inference Llama 2 in one file of pure Cuda
MIT License
16
stars
2
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Probable case not considered
#6
obhalerao97
opened
8 months ago
3
parallelize part of logits processing
#5
kroggen
opened
1 year ago
6
speed-up softmax
#4
kroggen
closed
1 year ago
4
rename variables
#3
kroggen
closed
1 year ago
4
fix build with CUDA 12.2
#2
kroggen
closed
1 year ago
2
update weighted sum of values
#1
kroggen
closed
1 year ago
3