| .. |
|
custom_modeling
|
fix(server): cleanup new flash past_key_values logic (#217)
|
2023-04-21 16:19:04 +02:00 |
|
__init__.py
|
feat(router): add git sha to info route (#208)
|
2023-04-19 21:36:59 +02:00 |
|
bloom.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
causal_lm.py
|
feat(router): use number of tokens in batch as input for dynamic batching (#226)
|
2023-04-24 17:59:00 +02:00 |
|
flash_causal_lm.py
|
feat(router): use number of tokens in batch as input for dynamic batching (#226)
|
2023-04-24 17:59:00 +02:00 |
|
flash_llama.py
|
fix(server): fix past key values logic (#216)
|
2023-04-21 15:59:18 +02:00 |
|
flash_neox.py
|
fix(server): fix past key values logic (#216)
|
2023-04-21 15:59:18 +02:00 |
|
flash_santacoder.py
|
fix(server): fix past key values logic (#216)
|
2023-04-21 15:59:18 +02:00 |
|
galactica.py
|
feat(router): use number of tokens in batch as input for dynamic batching (#226)
|
2023-04-24 17:59:00 +02:00 |
|
gpt_neox.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
model.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
opt.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
santacoder.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
seq2seq_lm.py
|
feat(router): use number of tokens in batch as input for dynamic batching (#226)
|
2023-04-24 17:59:00 +02:00 |
|
t5.py
|
feat(router): add device and dtype info (#215)
|
2023-04-21 15:36:29 +02:00 |
|
types.py
|
feat(router): drop requests when client closes the channel (#202)
|
2023-04-20 11:07:40 +02:00 |
ebc74d5666