update flash

app.py

@@ -5,6 +5,9 @@ from decord import VideoReader, cpu
 import os
 import spaces
 
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 # Load the model and tokenizer
 model_name = "openbmb/MiniCPM-V-2_6-int4"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

requirements.txt

@@ -1,9 +1,8 @@
 Pillow==10.1.0
-torch==2.1.2+cu118
+torch==2.1.2
 torchvision==0.16.2
 transformers==4.40.0
 sentencepiece==0.1.99
 accelerate==0.30.1
 bitsandbytes==0.43.1
 decord
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu118torch1.12cxx11abiFALSE-cp310-cp310-linux_x86_64.whl