Add support for Microsoft Phi-3 model to DeepSpeed-FastGen #5559
Add support for Microsoft Phi-3 model to DeepSpeed-FastGen
eb636acd
Fix fused GatedMLP to comply with inference v2 format
4bf4b0f2
Add link to FastGen blog
13260fb1
Rename Phi to Phi3
e79d4b4d
adk9
force pushed
from
3a678e80
to
e79d4b4d
1 year ago
Fix formatting
cec78ee1
adk9
marked this pull request as ready for review 1 year ago
Merge branch 'master' into adk9/phi3-inference
43010775
Phi-3 mini has no unmapped param
702bad7e
adk9
force pushed
from
0b59cdb0
to
702bad7e
1 year ago
adk9
force pushed
from
dd4868fe
to
702bad7e
1 year ago
Merge branch 'master' into adk9/phi3-inference
24176bdd
Merge branch 'master' into adk9/phi3-inference
471ac01b
Merge branch 'master' into adk9/phi3-inference
8becbba0
HeyangQin
approved these changes
on 2024-07-15
Merge branch 'master' into adk9/phi3-inference
8f8b0320
loadams
enabled auto-merge 1 year ago
loadams
merged
6a163e03
into master 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub