diff --git a/backends/exllamav2/utils.py b/backends/exllamav2/utils.py
index 5b1d5678..a5e8779e 100644
--- a/backends/exllamav2/utils.py
+++ b/backends/exllamav2/utils.py
@@ -7,7 +7,7 @@
 def check_exllama_version():
     """Verifies the exllama version"""
 
-    required_version = version.parse("0.1.6")
+    required_version = version.parse("0.1.7")
     current_version = version.parse(package_version("exllamav2").split("+")[0])
 
     unsupported_message = (
diff --git a/pyproject.toml b/pyproject.toml
index 9d9aaf8a..836113b5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -58,12 +58,12 @@ cu121 = [
     "torch @ https://download.pytorch.org/whl/cu121/torch-2.3.1%2Bcu121-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
 
     # Exl2
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp312-cp312-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.12'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp311-cp311-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.11'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp310-cp310-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.10'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu121.torch2.3.1-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp312-cp312-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.12'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp311-cp311-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.11'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp310-cp310-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.10'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu121.torch2.3.1-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
 
     # Windows FA2 from https://github.com/bdashore3/flash-attention/releases
     "flash_attn @ https://github.com/bdashore3/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3.1cxx11abiFALSE-cp312-cp312-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.12'",
@@ -85,12 +85,12 @@ cu118 = [
     "torch @ https://download.pytorch.org/whl/cu118/torch-2.3.1%2Bcu118-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
 
     # Exl2
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp312-cp312-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.12'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp311-cp311-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.11'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp310-cp310-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.10'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+cu118.torch2.3.1-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp312-cp312-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.12'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp311-cp311-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.11'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp310-cp310-win_amd64.whl ; platform_system == 'Windows' and python_version == '3.10'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.11'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+cu118.torch2.3.1-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.10'",
 
     # Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
     "flash_attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu118torch2.3cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and platform_machine == 'x86_64' and python_version == '3.12'",
@@ -109,9 +109,9 @@ amd = [
     "torch @ https://download.pytorch.org/whl/rocm6.0/torch-2.3.1%2Brocm6.0-cp310-cp310-linux_x86_64.whl ; python_version == '3.10'",
 
     # Exl2
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+rocm6.0.torch2.3.1-cp312-cp312-linux_x86_64.whl ; python_version == '3.12'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+rocm6.0.torch2.3.1-cp311-cp311-linux_x86_64.whl ; python_version == '3.11'",
-    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.6/exllamav2-0.1.6+rocm6.0.torch2.3.1-cp310-cp310-linux_x86_64.whl ; python_version == '3.10'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+rocm6.0.torch2.3.1-cp312-cp312-linux_x86_64.whl ; python_version == '3.12'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+rocm6.0.torch2.3.1-cp311-cp311-linux_x86_64.whl ; python_version == '3.11'",
+    "exllamav2 @ https://github.com/turboderp/exllamav2/releases/download/v0.1.7/exllamav2-0.1.7+rocm6.0.torch2.3.1-cp310-cp310-linux_x86_64.whl ; python_version == '3.10'",
 ]
 
 # MARK: Ruff options