tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Remove seq_len arg in rotary_emb (#1443)

Browse Source 
* remove seq_len in llama rotary_emb

* chore: lint

---------

Co-authored-by: Wing Lian <wing.lian@gmail.com>
This commit is contained in:
WenboPan
2024-03-27 03:19:44 +08:00
committed by GitHub
parent bcdc9b1601
commit e07347b188
2 changed files with 3 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/axolotl/monkeypatch/llama_attn_hijack_flash.py
View File

@@ -284,12 +284,7 @@ def flashattn_forward_with_s2attn(
# [bsz, nh, q_len, hd]
# pylint: disable=duplicate-code
kv_seq_len = key_states.shape[-2]
if past_key_value is not None:
kv_seq_len += past_key_value[0].shape[-2]
cos, sin = self.rotary_emb(
value_states, seq_len=kv_seq_len, position_ids=position_ids
)
cos, sin = self.rotary_emb(value_states, position_ids=position_ids)
query_states, key_states = apply_rotary_pos_emb(
query_states, key_states, cos, sin, position_ids
)
@@ -435,13 +430,7 @@ def flashattn_forward(
# [bsz, q_len, nh, hd]
# [bsz, nh, q_len, hd]
kv_seq_len = key_states.shape[-2]
if past_key_value is not None:
kv_seq_len += past_key_value[0].shape[-2]
cos, sin = self.rotary_emb(
value_states, seq_len=kv_seq_len, position_ids=position_ids
)
cos, sin = self.rotary_emb(value_states, position_ids=position_ids)
query_states, key_states = apply_rotary_pos_emb(
query_states, key_states, cos, sin, position_ids
)

6
src/axolotl/monkeypatch/llama_attn_hijack_xformers.py
View File

@@ -80,11 +80,7 @@ def xformers_forward(
# [bsz, q_len, nh, hd]
# [bsz, nh, q_len, hd]
kv_seq_len = key_states.shape[-2]
if past_key_value is not None:
kv_seq_len += past_key_value[0].shape[-2]
cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
cos, sin = self.rotary_emb(value_states)
query_states, key_states = apply_rotary_pos_emb(
query_states, key_states, cos, sin, position_ids
)