hf_text-generation-inference/server/text_generation_server/models
OlivierDehaene e9669a4085
feat(server): do not use device_map auto on single GPU (#362)
2023-05-23 19:12:12 +02:00
..
custom_modeling fix(server): fix init for flash causal lm (#352) 2023-05-22 15:05:32 +02:00
__init__.py Hotfixes for santacoder/bigcode. (#294) 2023-05-15 10:35:20 +02:00
bloom.py feat(server): support fp16 for t5 (#360) 2023-05-23 18:16:48 +02:00
causal_lm.py feat(server): do not use device_map auto on single GPU (#362) 2023-05-23 19:12:12 +02:00
flash_causal_lm.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
flash_llama.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
flash_neox.py fix(server): fix init for flash causal lm (#352) 2023-05-22 15:05:32 +02:00
flash_santacoder.py fix(server): fix init for flash causal lm (#352) 2023-05-22 15:05:32 +02:00
galactica.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
gpt_neox.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
model.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
opt.py fix(server): fix init for flash causal lm (#352) 2023-05-22 15:05:32 +02:00
santacoder.py fix(server): fix decode token (#334) 2023-05-16 23:23:27 +02:00
seq2seq_lm.py feat(server): do not use device_map auto on single GPU (#362) 2023-05-23 19:12:12 +02:00
t5.py feat(server): support fp16 for t5 (#360) 2023-05-23 18:16:48 +02:00
types.py feat(router): drop requests when client closes the channel (#202) 2023-04-20 11:07:40 +02:00