DeepSpeed
Extend scratch buffer for long prompts
#2212
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
27
Changes
View On
GitHub
Extend scratch buffer for long prompts
#2212
jeffra
merged 27 commits into
master
from
cholmes/fix-long-seq-len-inference
Extend scratch buffer for long prompts
48449661
cmikeh2
requested a review
from
jeffra
3 years ago
cmikeh2
requested a review
from
samyam
3 years ago
cmikeh2
requested a review
from
tjruwase
3 years ago
cmikeh2
requested a review
from
ShadenSmith
3 years ago
cmikeh2
requested a review
from
conglongli
3 years ago
cmikeh2
requested a review
from
awan-10
3 years ago
cmikeh2
requested a review
from
cli99
3 years ago
cmikeh2
requested a review
from
eltonzheng
3 years ago
cmikeh2
requested a review
from
minjiaz
3 years ago
cmikeh2
requested a review
from
RezaYazdaniAminabadi
3 years ago
cmikeh2
requested a review
from
duli2012
3 years ago
cmikeh2
requested a review
from
mrwyattii
3 years ago
cmikeh2
requested a review
from
yaozhewei
3 years ago
cmikeh2
requested a review
from
arashb
3 years ago
cmikeh2
requested a review
from
xiaoxiawu-microsoft
3 years ago
cmikeh2
requested a review
from
samadejacobs
3 years ago
Merge branch 'master' into cholmes/fix-long-seq-len-inference
be4714d7
RezaYazdaniAminabadi
commented on 2022-08-12
RezaYazdaniAminabadi
commented on 2022-08-12
Fetch correct tail buffer for batched inputs.
c6411d13
Style change
c074ed37
Merge branch 'cholmes/fix-long-seq-len-inference' of https://github.c…
31357744
Merge branch 'master' into cholmes/fix-long-seq-len-inference
777a36ec
Fix variable rename
ec6b1ad3
Merge branch 'cholmes/fix-long-seq-len-inference' of https://github.c…
d897f98f
Merge branch 'master' into cholmes/fix-long-seq-len-inference
6da92341
Reduce maximum sequence length
606d3447
Merge branch 'master' into cholmes/fix-long-seq-len-inference
5269ba10
Merge branch 'master' into cholmes/fix-long-seq-len-inference
89f2dedf
Merge branch 'master' into cholmes/fix-long-seq-len-inference
8e298087
Add debug print
c8243304
Merge branch 'master' into cholmes/fix-long-seq-len-inference
d9eb076b
Multi-batch inference fix
aafba00c
add batch-size at the tranform launch for the half-precision implemen…
4abd4555
Merge branch 'master' into cholmes/fix-long-seq-len-inference
603cc5bf
Merge branch 'master' into cholmes/fix-long-seq-len-inference
508712a7
RezaYazdaniAminabadi
requested a review
from
GuanhuaWang
3 years ago
no need to throw error when there is no mask passed
51a63715
Merge branch 'cholmes/fix-long-seq-len-inference' of github.com:micro…
9effa9e4
Merge branch 'master' into cholmes/fix-long-seq-len-inference
c9652ecf
Increasing the token-length based on available memory for GPT models …
d8f52032
Merge branch 'master' into cholmes/fix-long-seq-len-inference
b64c1170
fix bert issue & remove some dead code
48a8b969
fix formating
c1d83f99
Merge branch 'master' into cholmes/fix-long-seq-len-inference
a5f4d31b
jeffra
approved these changes on 2022-09-23
jeffra
merged
3d097bb8
into master
3 years ago
jeffra
deleted the cholmes/fix-long-seq-len-inference branch
3 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
jeffra
RezaYazdaniAminabadi
samyam
tjruwase
ShadenSmith
conglongli
awan-10
cli99
eltonzheng
minjiaz
duli2012
mrwyattii
yaozhewei
arashb
xiaoxiawu-microsoft
samadejacobs
GuanhuaWang
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub