diff --git a/.github/workflows/multi-gpu-e2e.yml b/.github/workflows/multi-gpu-e2e.yml
index 745e177bb..833dc4f29 100644
--- a/.github/workflows/multi-gpu-e2e.yml
+++ b/.github/workflows/multi-gpu-e2e.yml
@@ -47,7 +47,8 @@ jobs:
             cuda_version: 13.0.0
             python_version: "3.11"
             pytorch: 2.9.1
-            axolotl_extras: fbgemm-gpu
+            axolotl_extras:
+#            axolotl_extras: fbgemm-gpu
             num_gpus: 2
             nightly_build: "true"
     runs-on: [self-hosted, modal]
diff --git a/requirements.txt b/requirements.txt
index 18ba0a6d1..285792611 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -13,7 +13,7 @@ packaging==23.2
 huggingface_hub>=0.36.0
 peft>=0.18.0
 tokenizers>=0.22.1
-transformers==4.57.1
+transformers==4.57.5
 accelerate==1.12.0
 datasets==4.4.2
 deepspeed>=0.18.3
diff --git a/setup.py b/setup.py
index 5f51dbee0..d98c7e19a 100644
--- a/setup.py
+++ b/setup.py
@@ -63,9 +63,19 @@ def parse_requirements(extras_require_map):
             else:
                 raise ValueError("Invalid version format")
 
+            torch_parts = torch_version.split("+")
+            if len(torch_parts) == 2:
+                torch_cuda_version = torch_parts[1]
+                _dependency_links.append(
+                    f"https://download.pytorch.org/whl/{torch_cuda_version}"
+                )
+
             if (major, minor) >= (2, 9):
                 extras_require_map.pop("fbgemm-gpu")
-                extras_require_map["fbgemm-gpu"] = ["fbgemm-gpu-genai==1.4.1"]
+                extras_require_map["fbgemm-gpu"] = [
+                    "fbgemm-gpu==1.4.0",
+                    "fbgemm-gpu-genai==1.4.2",
+                ]
                 extras_require_map["vllm"] = ["vllm==0.11.1"]
                 if not install_xformers:
                     _install_requires.pop(_install_requires.index(xformers_version))