.. |
__init__.py
|
05faa0b3c8
add quantization script for cpu
|
3 jaren geleden |
config.json
|
a798ea04a6
add minimalistic benchmarks
|
3 jaren geleden |
convert_model.py
|
a2634001e9
Reduce vocabulary size in test model, fix bug in routing when overlapped (#45)
|
3 jaren geleden |
deploy_server.sh
|
11a424837f
integrate mixed-8bit model (#39)
|
3 jaren geleden |
inference_one_block.py
|
4695071ad2
WIP: make DistributedBloom compliant with HF interface
|
3 jaren geleden |
local_server_config_example.cfg
|
f60a7dd183
deploy swarm on local & remote machines
|
3 jaren geleden |
remote_server_config_example.cfg
|
f60a7dd183
deploy swarm on local & remote machines
|
3 jaren geleden |
run_local_servers.sh
|
11a424837f
integrate mixed-8bit model (#39)
|
3 jaren geleden |
run_remote_servers.sh
|
6573076883
Sequential and parallel forward / backward (#36)
|
3 jaren geleden |
run_server.py
|
d94549eda8
review
|
3 jaren geleden |
speed_test.py
|
e2711a033b
Add automated tests (#23)
|
3 jaren geleden |