issues
search
hpcaitech
/
EnergonAI
Large-scale model inference.
Apache License 2.0
630
stars
90
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
inference of pre-trained model
#125
Emerald01
opened
2 years ago
1
[opt] add async executor
#124
ver217
closed
2 years ago
0
make the generation task within the engine
#123
dujiangsu
closed
2 years ago
0
add serving queue
#122
dujiangsu
closed
2 years ago
0
[opt] generate api receives top_k, top_p, and temperature
#121
ver217
closed
2 years ago
0
[model] support topk, topp, temperature when generating
#120
ver217
closed
2 years ago
0
[docker] polish lauch docker scripts
#119
feifeibear
closed
2 years ago
0
[example] refactor opt
#118
ver217
closed
2 years ago
0
add benchmark
#117
ver217
closed
2 years ago
0
refactor opt server api
#116
ver217
closed
2 years ago
0
fix hf gpt2 example
#115
ver217
closed
2 years ago
0
refactor tp load checkpoint
#114
ver217
closed
2 years ago
0
refactor load_checkpoint
#113
ver217
closed
2 years ago
0
[NFC] global var should be in uppercase
#112
feifeibear
closed
2 years ago
0
add opt example
#111
ver217
closed
2 years ago
0
Remove hard code directory path
#110
feifeibear
opened
2 years ago
0
[docker] add test_query.sh and update docker file
#109
feifeibear
closed
2 years ago
0
change rpc timeout
#108
dujiangsu
closed
2 years ago
0
[docker] add dockerfile and change hardcode path
#107
feifeibear
closed
2 years ago
0
Provide a docker service
#106
feifeibear
closed
2 years ago
0
add linear func
#105
oahzxl
closed
2 years ago
0
add linear func
#104
oahzxl
closed
2 years ago
0
modify offload manager and add linear example
#103
MaruyamaAya
closed
2 years ago
0
OPT inference generate example
#102
virgulvirgul
opened
2 years ago
1
tTemporarily stop kernels for correctness
#101
dujiangsu
closed
2 years ago
0
Missing energonai_linear_func in setup.py
#100
xgreat8
opened
2 years ago
1
Connection refused on docker exposed port
#99
xgreat8
opened
2 years ago
1
update readme
#98
dujiangsu
closed
2 years ago
0
timer with ignrore the first func
#97
dujiangsu
closed
2 years ago
0
fix bug in batch manager
#96
dujiangsu
closed
2 years ago
0
match checkpoint for opt
#95
dujiangsu
closed
2 years ago
0
add basic model as component
#94
dujiangsu
closed
2 years ago
0
add offload manager
#93
MaruyamaAya
closed
2 years ago
0
fix batch wrapping bug
#92
MaruyamaAya
closed
2 years ago
0
update batcher for pipeline
#91
dujiangsu
closed
2 years ago
0
Feature/load balanced pipe
#90
dujiangsu
closed
2 years ago
0
[Feature]: Automatic Pipeline Parallelism
#89
dujiangsu
opened
2 years ago
0
update Readme
#88
dujiangsu
closed
2 years ago
0
update Readme
#87
dujiangsu
closed
2 years ago
0
add comments and delete unnecessary codes.
#86
MaruyamaAya
closed
2 years ago
0
refactor batch manager related files
#85
MaruyamaAya
closed
2 years ago
0
update readme
#84
dujiangsu
closed
2 years ago
0
update readme
#83
dujiangsu
closed
2 years ago
0
Link TensorRT as backend for single device execution
#82
dujiangsu
closed
2 years ago
0
Feature/trt
#81
dujiangsu
closed
2 years ago
0
update metaconfig
#80
dujiangsu
closed
2 years ago
0
update metaconfig
#79
dujiangsu
closed
2 years ago
0
make config globally available
#78
dujiangsu
closed
2 years ago
0
change project name
#77
dujiangsu
closed
2 years ago
0
Update README.md
#76
dujiangsu
closed
2 years ago
0
Previous
Next