diff --git a/requirements.txt b/requirements.txt
index d18a28b5..dc7c231e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -33,8 +33,8 @@ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_
 # CUDA wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 7a85436c..e6078e59 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -32,6 +32,6 @@ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_
 
 # AMD wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index ec91c4c3..7b104fb0 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -32,5 +32,5 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/
 
 # AMD wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index 7df47cdd..d5e4ef51 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -33,8 +33,8 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/
 # CUDA wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"