| .. |
|
custom_modeling
|
feat(server): support quantization for flash models (#200)
|
2023-04-19 12:51:11 +02:00 |
|
__init__.py
|
feat(router): add git sha to info route (#208)
|
2023-04-19 21:36:59 +02:00 |
|
bloom.py
|
feat(server): support sharded santacoder (#167)
|
2023-04-12 17:18:08 +02:00 |
|
causal_lm.py
|
feat(router): drop requests when client closes the channel (#202)
|
2023-04-20 11:07:40 +02:00 |
|
flash_causal_lm.py
|
feat(server): flash attention past key value optimizations (#213)
|
2023-04-21 14:57:18 +02:00 |
|
flash_llama.py
|
feat(server): support quantization for flash models (#200)
|
2023-04-19 12:51:11 +02:00 |
|
flash_neox.py
|
feat(server): support quantization for flash models (#200)
|
2023-04-19 12:51:11 +02:00 |
|
flash_santacoder.py
|
feat(server): support quantization for flash models (#200)
|
2023-04-19 12:51:11 +02:00 |
|
galactica.py
|
feat(router): drop requests when client closes the channel (#202)
|
2023-04-20 11:07:40 +02:00 |
|
gpt_neox.py
|
feat(server): support sharded santacoder (#167)
|
2023-04-12 17:18:08 +02:00 |
|
model.py
|
feat(server): optimize decode for sane tokenizers (#170)
|
2023-04-12 12:03:10 +02:00 |
|
opt.py
|
feat(server): support sharded santacoder (#167)
|
2023-04-12 17:18:08 +02:00 |
|
santacoder.py
|
feat(server): optimize decode for sane tokenizers (#170)
|
2023-04-12 12:03:10 +02:00 |
|
seq2seq_lm.py
|
feat(router): drop requests when client closes the channel (#202)
|
2023-04-20 11:07:40 +02:00 |
|
t5.py
|
feat(server): support sharded santacoder (#167)
|
2023-04-12 17:18:08 +02:00 |
|
types.py
|
feat(router): drop requests when client closes the channel (#202)
|
2023-04-20 11:07:40 +02:00 |
ac8c0f6fe4