From 232658f9a8ba6060e0c10b5fd0dc8128064550d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Iv=C3=A1n=20Baldo?= Date: Wed, 31 Jan 2024 15:21:54 -0300 Subject: [PATCH 1/3] Make MarkdownLint happy. --- powerinfer/README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/powerinfer/README.md b/powerinfer/README.md index a72ad06..13bae21 100644 --- a/powerinfer/README.md +++ b/powerinfer/README.md @@ -1,4 +1,6 @@ -[PowerInfer](https://github.com/SJTU-IPADS/PowerInfer) +#PowerInfer benchmark + +Benchmark for [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer). Note that the model loses some inference quality in exchange for speed as shown in https://huggingface.co/SparseLLM/ReluLLaMA-7B. From ade534eacc6e0c753a5ec1e0b6bfe87b7804a0f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Iv=C3=A1n=20Baldo?= Date: Wed, 31 Jan 2024 15:29:55 -0300 Subject: [PATCH 2/3] Make Kics happier. --- powerinfer/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/powerinfer/Dockerfile b/powerinfer/Dockerfile index 5d68019..5caad21 100644 --- a/powerinfer/Dockerfile +++ b/powerinfer/Dockerfile @@ -43,7 +43,7 @@ FROM nvidia/cuda:12.3.1-devel-rockylinux9 ARG USERID=1000 RUN yum install -y python3-pip cmake libcudnn8 git && yum clean all && rm -rf /var/cache/yum/* RUN git clone https://github.com/SJTU-IPADS/PowerInfer -WORKDIR PowerInfer +WORKDIR /PowerInfer RUN pip install --no-cache-dir -r requirements.txt RUN cmake -S . -B build -DLLAMA_CUBLAS=ON RUN cmake --build build --config Release -j $(nproc) From f81e384cfda266737204d28161492fbb2f369b7a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Iv=C3=A1n=20Baldo?= Date: Wed, 31 Jan 2024 15:32:47 -0300 Subject: [PATCH 3/3] Make Hadolint happier. --- powerinfer/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/powerinfer/Dockerfile b/powerinfer/Dockerfile index 5caad21..a1de8fe 100644 --- a/powerinfer/Dockerfile +++ b/powerinfer/Dockerfile @@ -46,7 +46,7 @@ RUN git clone https://github.com/SJTU-IPADS/PowerInfer WORKDIR /PowerInfer RUN pip install --no-cache-dir -r requirements.txt RUN cmake -S . -B build -DLLAMA_CUBLAS=ON -RUN cmake --build build --config Release -j $(nproc) +RUN cmake --build build --config Release -j "$(nproc)" RUN pip install --no-cache-dir pandas #for the benchmark. RUN adduser -u $USERID user USER user