Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feat] Sage Attention Support for Triton kernel #929

Open
wants to merge 12 commits into
base: develop
Choose a base branch
from
6 changes: 3 additions & 3 deletions paddlemix/models/audioldm2/clap_module/clap.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,13 @@

from .model import CLAP, CLAPAudioCfg, CLAPTextCfg
import dataclasses
from dataclasses import dataclass
from dataclasses import dataclass, field

@dataclass
class CLAPConfig:
embed_dim: int = 1024
audio_cfg: CLAPAudioCfg = CLAPAudioCfg()
text_cfg: CLAPTextCfg = CLAPTextCfg()
audio_cfg: CLAPAudioCfg = field(default_factory=CLAPAudioCfg)
text_cfg: CLAPTextCfg = field(default_factory=CLAPTextCfg)

def create_clap_model(
amodel_name: str,
Expand Down
6 changes: 6 additions & 0 deletions paddlemix/triton_ops/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,9 @@
split_concat,
triton_split,
weight_only_int8,
sageattn_quant_per_block_int8,
sageattn_forward_casual_false,
sageattn_qk_int8_pv_fp16_triton
)
from .triton_utils import (
get_dtype_str,
Expand All @@ -43,6 +46,9 @@
"fused_rotary_emb",
"split_concat",
"triton_split",
"sageattn_quant_per_block_int8",
"sageattn_forward_casual_false",
"sageattn_qk_int8_pv_fp16_triton"
]
except:
pass
Loading