diff --git a/README.md b/README.md
index 119098f5c..e4cff01a9 100644
--- a/README.md
+++ b/README.md
@@ -203,7 +203,7 @@ Put your VAE in: models/vae
 ### AMD GPUs (Linux only)
 AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
 
-```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.3```
+```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4```
 
 This is the command to install the nightly with ROCm 6.4 which might have some performance improvements:
 
@@ -237,7 +237,7 @@ Additional discussion and help can be found [here](https://github.com/comfyanony
 
 Nvidia users should install stable pytorch using this command:
 
-```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu128```
+```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu129```
 
 This is the command to install pytorch nightly instead which might have performance improvements.
 
diff --git a/comfy/lora.py b/comfy/lora.py
index 6686b7229..00358884b 100644
--- a/comfy/lora.py
+++ b/comfy/lora.py
@@ -301,6 +301,7 @@ def model_lora_keys_unet(model, key_map={}):
                 key_map["{}".format(key_lora)] = k
                 # Support transformer prefix format
                 key_map["transformer.{}".format(key_lora)] = k
+                key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = k #SimpleTuner lycoris format
 
     return key_map
 
diff --git a/comfy/model_management.py b/comfy/model_management.py
index 9e6149d60..c08f759e5 100644
--- a/comfy/model_management.py
+++ b/comfy/model_management.py
@@ -321,9 +321,9 @@ try:
             if torch_version_numeric >= (2, 7):  # works on 2.6 but doesn't actually seem to improve much
                 if any((a in arch) for a in ["gfx90a", "gfx942", "gfx1100", "gfx1101", "gfx1151"]):  # TODO: more arches, TODO: gfx950
                     ENABLE_PYTORCH_ATTENTION = True
-            if torch_version_numeric >= (2, 8):
-                if any((a in arch) for a in ["gfx1201"]):
-                    ENABLE_PYTORCH_ATTENTION = True
+#            if torch_version_numeric >= (2, 8):
+#                if any((a in arch) for a in ["gfx1201"]):
+#                    ENABLE_PYTORCH_ATTENTION = True
         if torch_version_numeric >= (2, 7) and rocm_version >= (6, 4):
             if any((a in arch) for a in ["gfx1201", "gfx942", "gfx950"]):  # TODO: more arches
                 SUPPORT_FP8_OPS = True
@@ -340,7 +340,7 @@ if ENABLE_PYTORCH_ATTENTION:
 
 PRIORITIZE_FP16 = False  # TODO: remove and replace with something that shows exactly which dtype is faster than the other
 try:
-    if is_nvidia() and PerformanceFeature.Fp16Accumulation in args.fast:
+    if (is_nvidia() or is_amd()) and PerformanceFeature.Fp16Accumulation in args.fast:
         torch.backends.cuda.matmul.allow_fp16_accumulation = True
         PRIORITIZE_FP16 = True  # TODO: limit to cards where it actually boosts performance
         logging.info("Enabled fp16 accumulation.")
diff --git a/execution.py b/execution.py
index 952f0cc5c..1dc35738b 100644
--- a/execution.py
+++ b/execution.py
@@ -646,8 +646,6 @@ class PromptExecutor:
             self.add_message("execution_error", mes, broadcast=False)
 
     def execute(self, prompt, prompt_id, extra_data={}, execute_outputs=[]):
-        asyncio_loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(asyncio_loop)
         asyncio.run(self.execute_async(prompt, prompt_id, extra_data, execute_outputs))
 
     async def execute_async(self, prompt, prompt_id, extra_data={}, execute_outputs=[]):
diff --git a/requirements.txt b/requirements.txt
index 87c1d835f..efdfdb8bf 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,6 @@
 comfyui-frontend-package==1.24.4
-comfyui-workflow-templates==0.1.52
-comfyui-embedded-docs==0.2.4
+comfyui-workflow-templates==0.1.53
+comfyui-embedded-docs==0.2.6
 torch
 torchsde
 torchvision
diff --git a/server.py b/server.py
index 0553a0dd7..8f9c88ebf 100644
--- a/server.py
+++ b/server.py
@@ -235,7 +235,7 @@ class PromptServer():
                                     sid,
                                 )
 
-                                logging.info(
+                                logging.debug(
                                     f"Feature flags negotiated for client {sid}: {client_flags}"
                                 )
                             first_message = False