huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 16:32:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Bump llama.cpp and switch to ggml-org

Browse Source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2025-02-20 15:57:45 +00:00
parent 0a55bd3db9
commit 3849223340
No known key found for this signature in database
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile_llamacpp
View File

@ -1,6 +1,6 @@
FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu24.04 AS deps FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu24.04 AS deps
ARG llamacpp_version=b4714 ARG llamacpp_version=b4747
ARG llamacpp_cuda=OFF ARG llamacpp_cuda=OFF
ARG cuda_arch=75-real;80-real;86-real;89-real;90-real ARG cuda_arch=75-real;80-real;86-real;89-real;90-real
@ -17,7 +17,7 @@ RUN apt update && apt upgrade -y && apt install -y \
pkg-config \ pkg-config \
tar tar
ADD https://github.com/ggerganov/llama.cpp/archive/refs/tags/${llamacpp_version}.tar.gz /opt/src/ ADD https://github.com/ggml-org/llama.cpp/archive/refs/tags/${llamacpp_version}.tar.gz /opt/src/
RUN mkdir -p llama.cpp \ RUN mkdir -p llama.cpp \
&& tar -xzf ${llamacpp_version}.tar.gz -C llama.cpp --strip-components=1 \ && tar -xzf ${llamacpp_version}.tar.gz -C llama.cpp --strip-components=1 \
&& cd llama.cpp \ && cd llama.cpp \