From 13a54729b1eae290e372e0228ac041d12f8ebc8b Mon Sep 17 00:00:00 2001
From: jllllll <3887729+jllllll@users.noreply.github.com>
Date: Tue, 26 Sep 2023 19:36:14 -0500
Subject: [PATCH] Bump exllamav2 to 0.0.4 and use pre-built wheels (#4095)

---
 requirements.txt                 | 4 +++-
 requirements_amd.txt             | 2 +-
 requirements_amd_noavx2.txt      | 2 +-
 requirements_apple_intel.txt     | 2 +-
 requirements_apple_silicon.txt   | 2 +-
 requirements_cpu_only.txt        | 2 +-
 requirements_cpu_only_noavx2.txt | 2 +-
 requirements_noavx2.txt          | 4 +++-
 requirements_nowheels.txt        | 2 +-
 9 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index c426123f..99fc52ab 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4; platform_system != "Darwin" and platform_machine != "x86_64"
 markdown
 numpy==1.24
 optimum==1.13.1
@@ -38,6 +38,8 @@ https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-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+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-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/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-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/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 4ed5e8c2..80fff14e 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index 13b258d3..e9ea866e 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index c719bd1c..bc257a84 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index 1ec81300..88ce7495 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt
index 5cc4c6f8..fa72fd18 100644
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt
index 4373e565..e43470f1 100644
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index e6fe0fe0..726449cb 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4; platform_system != "Darwin" and platform_machine != "x86_64"
 markdown
 numpy==1.24
 optimum==1.13.1
@@ -38,6 +38,8 @@ https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-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+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-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/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-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/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt
index 51a1e979..4b5c4f5e 100644
--- a/requirements_nowheels.txt
+++ b/requirements_nowheels.txt
@@ -8,7 +8,7 @@ accelerate==0.23.*
 colorama
 datasets
 einops
-exllamav2==0.0.3
+exllamav2==0.0.4
 markdown
 numpy==1.24
 optimum==1.13.1