DeepSpeed
Fixing inference api for FP32 and non-masking GPT-based models
#1204
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
Fixing inference api for FP32 and non-masking GPT-based models
#1204
jeffra
merged 6 commits into
master
from
reyazda/fix-inference-api
fixing inference api for FP32 and non-masking GPT-based models
db492f60
RezaYazdaniAminabadi
requested a review
from
awan-10
4 years ago
RezaYazdaniAminabadi
requested a review
from
cli99
4 years ago
RezaYazdaniAminabadi
requested a review
from
conglongli
4 years ago
RezaYazdaniAminabadi
requested a review
from
eltonzheng
4 years ago
RezaYazdaniAminabadi
requested a review
from
jeffra
4 years ago
RezaYazdaniAminabadi
requested a review
from
minjiaz
4 years ago
RezaYazdaniAminabadi
requested a review
from
niumanar
4 years ago
RezaYazdaniAminabadi
requested a review
from
samyam
4 years ago
RezaYazdaniAminabadi
requested a review
from
ShadenSmith
4 years ago
RezaYazdaniAminabadi
requested a review
from
tjruwase
4 years ago
use a dummy tensor if input_mask is none
e628299f
fix input_mask
485201bf
minor fix
65f1fe82
send input_mask to compute_attn func for checking
7cb65cc9
Merge branch 'master' into reyazda/fix-inference-api
79ee82f6
jeffra
approved these changes on 2021-07-20
jeffra
merged
6ba96289
into master
4 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
jeffra
awan-10
cli99
conglongli
eltonzheng
minjiaz
niumanar
samyam
ShadenSmith
tjruwase
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub