From 0b552220aa72113784590df263b519d308be1e1d Mon Sep 17 00:00:00 2001 From: Ashley Kleynhans Date: Fri, 19 Apr 2024 09:45:31 +0200 Subject: [PATCH] Bump ExLlamaV2 to version 0.0.19 --- Dockerfile | 6 ++++++ docker-bake.hcl | 2 +- oobabooga/requirements.txt | 10 +++++----- 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/Dockerfile b/Dockerfile index d46f24c..59f7948 100644 --- a/Dockerfile +++ b/Dockerfile @@ -30,6 +30,12 @@ COPY oobabooga/requirements* ./ RUN source /venv/bin/activate && \ pip3 install -r requirements.txt && \ bash -c 'for req in extensions/*/requirements.txt ; do pip3 install -r "$req" ; done' && \ +# mkdir -p repositories && \ +# cd repositories && \ +# git clone https://github.com/turboderp/exllamav2 && \ +# cd exllamav2 && \ +# pip3 install -r requirements.txt && \ +# pip3 install . && \ deactivate # Fix safetensors module broken by above exllama repository installation diff --git a/docker-bake.hcl b/docker-bake.hcl index 4204343..b606537 100644 --- a/docker-bake.hcl +++ b/docker-bake.hcl @@ -11,7 +11,7 @@ variable "APP" { } variable "RELEASE" { - default = "1.17.2" + default = "1.18.0" } variable "CU_VERSION" { diff --git a/oobabooga/requirements.txt b/oobabooga/requirements.txt index f4d1ac1..af5dbaf 100644 --- a/oobabooga/requirements.txt +++ b/oobabooga/requirements.txt @@ -56,11 +56,11 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu1 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/turboderp/exllamav2/releases/download/v0.0.17/exllamav2-0.0.17+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/turboderp/exllamav2/releases/download/v0.0.17/exllamav2-0.0.17+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/turboderp/exllamav2/releases/download/v0.0.17/exllamav2-0.0.17+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/turboderp/exllamav2/releases/download/v0.0.17/exllamav2-0.0.17+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/turboderp/exllamav2/releases/download/v0.0.17/exllamav2-0.0.17-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" +https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"