PanQiWei 26dc6852fe support inherit one of the three fused attention class and customize attn_bias building logic		2023-08-07 18:59:04 +08:00
..
__init__.py	Add support for InternLM	2023-07-07 09:25:40 -07:00
_base.py	mark fused ops injection as experiment features	2023-08-06 15:05:28 +08:00
_const.py	add fused attention injection logic to llama	2023-08-07 13:45:37 +08:00
_utils.py	Merge branch 'main' into peft_integration	2023-05-28 16:23:38 +08:00
auto.py	implement gptj attention and mlp fused ops injection logic	2023-08-06 14:55:06 +08:00
baichuan.py	Rename the class to match reference capitalisation	2023-06-18 21:01:07 +03:00
bloom.py	support dispatch layers to different devices when loading pretrained model before quantization	2023-04-27 02:24:08 +08:00
codegen.py	Add support for CodeGen/2	2023-05-08 17:34:00 +03:00
gpt2.py	fix device mismatch when directly using model to inference after quantization	2023-04-28 16:41:46 +08:00
gpt_bigcode.py	Add support for GPTBigCode	2023-05-08 12:28:29 +03:00
gpt_neox.py	support dispatch layers to different devices when loading pretrained model before quantization	2023-04-27 02:24:08 +08:00
gptj.py	support inherit one of the three fused attention class and customize attn_bias building logic	2023-08-07 18:59:04 +08:00
internlm.py	Add support for InternLM	2023-07-07 09:25:40 -07:00
llama.py	support inherit one of the three fused attention class and customize attn_bias building logic	2023-08-07 18:59:04 +08:00
moss.py	remove non-parameters module from MOSSGPTQForCausalLM.outside_layer_modules	2023-04-29 10:58:29 +08:00
opt.py	remove override of _resize_attention_mask for llama and opt	2023-04-28 23:08:42 +08:00
rw.py	support falcon	2023-05-27 07:53:39 +09:00