diff --git a/modules/util/triton_mm_8bit.py b/modules/util/triton_mm_8bit.py
index 8250e1270..522959d89 100644
--- a/modules/util/triton_mm_8bit.py
+++ b/modules/util/triton_mm_8bit.py
@@ -47,7 +47,7 @@
 )
 
 @triton.jit
-def __mm_kernel(
+def _mm_kernel(
         a_ptr, b_ptr, c_ptr,
         M, N, K,
         stride_am, stride_ak,
@@ -109,7 +109,7 @@ def mm_8bit(a: torch.Tensor, b: torch.Tensor) -> torch.Tensor:
 
     def grid(META):
         return (triton.cdiv(N, META['BLOCK_SIZE_N']) , triton.cdiv(M, META['BLOCK_SIZE_M']), )
-    __mm_kernel[grid](
+    _mm_kernel[grid](
         a, b, c,
         M, N, K,
         a.stride(0), a.stride(1),
diff --git a/requirements-cuda.txt b/requirements-cuda.txt
index c17429e6f..35c3059d7 100644
--- a/requirements-cuda.txt
+++ b/requirements-cuda.txt
@@ -1,10 +1,10 @@
 # pytorch
 --extra-index-url https://download.pytorch.org/whl/cu128
-torch==2.8.0+cu128
-torchvision==0.23.0+cu128
-onnxruntime-gpu==1.22.0
-nvidia-nccl-cu12==2.27.3; sys_platform == "linux"
-triton-windows==3.4.0.post20; sys_platform == "win32"
+torch==2.9.1+cu128
+torchvision==0.24.1+cu128
+onnxruntime-gpu==1.23.2
+nvidia-nccl-cu12==2.27.5; sys_platform == "linux"
+triton-windows==3.5.1.post24; sys_platform == "win32"
 
 # optimizers
-bitsandbytes==0.46.0 # bitsandbytes for 8-bit optimizers and weight quantization
+bitsandbytes==0.49.1 # bitsandbytes for 8-bit optimizers and weight quantization
diff --git a/requirements-default.txt b/requirements-default.txt
index cd8f93df4..06590561c 100644
--- a/requirements-default.txt
+++ b/requirements-default.txt
@@ -1,7 +1,7 @@
 # pytorch
-torch==2.8.0
-torchvision==0.23.0
-onnxruntime==1.22.1
+torch==2.9.1
+torchvision==0.24.1
+onnxruntime==1.23.2
 
 # optimizers
 # TODO
diff --git a/requirements-global.txt b/requirements-global.txt
index afa429bf2..133dd2b15 100644
--- a/requirements-global.txt
+++ b/requirements-global.txt
@@ -8,21 +8,21 @@ PyYAML==6.0.2
 huggingface-hub==0.34.4
 scipy==1.15.3
 matplotlib==3.10.3
-av==14.4.0
+av==16.1.0
 yt-dlp  #no pinned version, frequently updated for compatibility with sites
 scenedetect==0.6.6
 
 # pytorch
-accelerate==1.7.0
-safetensors==0.5.3
-tensorboard==2.19.0
-pytorch-lightning==2.5.1.post0
+accelerate==1.12.0
+safetensors==0.7.0
+tensorboard==2.20.0
+pytorch-lightning==2.6.0
 
 # diffusion models
 #Note: check whether Qwen bugs in diffusers have been fixed before upgrading diffusers (see BaseQwenSetup):
 -e git+https://github.com/huggingface/diffusers.git@256e010#egg=diffusers
 gguf==0.17.1
-transformers==4.56.2
+transformers==4.57.3
 sentencepiece==0.2.1 # transitive dependency of transformers for tokenizer loading
 omegaconf==2.3.0 # needed to load stable diffusion from single ckpt files
 invisible-watermark==0.2.0 # needed for the SDXL pipeline
diff --git a/requirements-rocm.txt b/requirements-rocm.txt
index 549156148..41a96d70a 100644
--- a/requirements-rocm.txt
+++ b/requirements-rocm.txt
@@ -3,9 +3,9 @@
 
 # pytorch
 --extra-index-url https://download.pytorch.org/whl/rocm6.3
-torch==2.7.1+rocm6.3  #intentionally not upgraded because of reported problems
-torchvision==0.22.1+rocm6.3
-onnxruntime==1.22.1
+torch==2.9.1+rocm6.3
+torchvision==0.24.1+rocm6.3
+onnxruntime==1.23.2
 
 # optimizers
 # TODO