Commit graph

12 commits

Author SHA1 Message Date
TheBloke
1b3329b399 Fix 'groupsize' -> 'group_size' in all other .py files. I haven't touched any CUDA kernels in case there's any complexity there I don't understand 2023-05-05 14:44:16 +01:00
qwopqwop200
208d660920
fix bug 2023-05-04 10:04:00 +09:00
qwopqwop200
f51a92ed79
support faster and model load strict 2023-05-04 09:53:28 +09:00
qwopqwop200
d8707f92a9
support fused_attn 2023-05-02 21:54:15 +09:00
qwopqwop200
f47322f073
fix bug 2023-05-02 21:14:27 +09:00
qwopqwop200
a6d4f5c091
fix bug 2023-05-02 19:19:04 +09:00
qwopqwop200
1388acac94
fix bug 2023-05-02 19:13:13 +09:00
qwopqwop200
f51f763fde
fused attn ,fused mlp apply 2023-05-02 18:51:04 +09:00
PanQiWei
b490ab004e remove override of _resize_attention_mask for llama and opt 2023-04-28 23:08:42 +08:00
PanQiWei
a2abff983e support dispatch layers to different devices when loading pretrained model before quantization 2023-04-27 02:24:08 +08:00
PanQiWei
a830a62bc3 fix bugs for attention_mask and position_ids 2023-04-20 18:32:21 +08:00
PanQiWei
229b61e20e first init 2023-04-14 01:09:40 +08:00