hf_text-generation-inference/server/text_generation_server/models
OlivierDehaene 745f596c88
feat(server): use float16 (#304)
2023-05-10 15:51:10 +02:00
..
custom_modeling feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
__init__.py feat(server): add watermarking tests (#248) 2023-04-27 19:16:35 +02:00
bloom.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
causal_lm.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
flash_causal_lm.py feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
flash_llama.py feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
flash_neox.py feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
flash_santacoder.py feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
galactica.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
gpt_neox.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
model.py feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
opt.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
santacoder.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
seq2seq_lm.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
t5.py feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
types.py feat(router): drop requests when client closes the channel (#202) 2023-04-20 11:07:40 +02:00