Vitaliy Chiley
vchiley
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Inference-Friendly Models With MixAttention
Organizations
vchiley's activity
add explicit cast where running without autocast causes issues
#41 opened over 1 year ago
by
vchiley
vchiley
add explicit cast where running without autocast causes issues
#60 opened over 1 year ago
by
vchiley
vchiley
add explicit cast where running without autocast causes issues
#48 opened over 1 year ago
by
vchiley
vchiley
add explicit cast where running without autocast causes issues
#26 opened over 1 year ago
by
vchiley
vchiley
add text-generation pipeline example with autocast
#40 opened over 1 year ago
by
vchiley
vchiley
add text-generation pipeline example with autocast
#25 opened over 1 year ago
by
vchiley
vchiley
add text-generation pipeline example with autocast
#47 opened over 1 year ago
by
vchiley
vchiley
add text-generation pipeline example with autocast
#59 opened over 1 year ago
by
vchiley
vchiley
Update modeling_mpt.py
#24 opened over 1 year ago
by
vchiley
vchiley
Update modeling_mpt.py
#39 opened over 1 year ago
by
vchiley
vchiley
Update modeling_mpt.py
#44 opened over 1 year ago
by
vchiley
vchiley
Update modeling_mpt.py
1
#55 opened over 1 year ago
by
daking
daking
Is it possible to add logic for handling output_attentions?
5
#30 opened over 1 year ago
by
abhinavkulkarni
abhinavkulkarni
Issue training With Triton
10
#40 opened over 1 year ago
by
MikeyBelllissimo
MikeyBelllissimo
updt flash_attn_triton import
#12 opened over 1 year ago
by
vchiley
vchiley
updt flash_attn_triton import
#23 opened over 1 year ago
by
vchiley
vchiley
updt flash_attn_triton import
#37 opened over 1 year ago
by
vchiley
vchiley
updt how flash_attn_triton is imported
#11 opened over 1 year ago
by
vchiley
vchiley
updt how flash_attn_triton is imported
#22 opened over 1 year ago
by
vchiley
vchiley
updt how flash_attn_triton is imported
#36 opened over 1 year ago
by
vchiley
vchiley