fix: flash attn wheel
Browse files- app.py +0 -4
- requirements.txt +2 -1
app.py
CHANGED
|
@@ -1,7 +1,3 @@
|
|
| 1 |
-
import sys
|
| 2 |
-
import subprocess
|
| 3 |
-
subprocess.check_call([sys.executable, "-m", "pip", "install", "flash-attn"])
|
| 4 |
-
|
| 5 |
import gradio as gr
|
| 6 |
import torch
|
| 7 |
import torchaudio
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
import torch
|
| 3 |
import torchaudio
|
requirements.txt
CHANGED
|
@@ -13,4 +13,5 @@ requests
|
|
| 13 |
openai
|
| 14 |
PyYAML
|
| 15 |
einops
|
| 16 |
-
huggingface_hub
|
|
|
|
|
|
| 13 |
openai
|
| 14 |
PyYAML
|
| 15 |
einops
|
| 16 |
+
huggingface_hub
|
| 17 |
+
https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.0.post2/flash_attn-2.8.0.post2+cu12torch2.7cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
|