COMMITS
/ .devops/full-cuda.Dockerfile November 17, 2024
J
docker: use GGML_NATIVE=OFF (#10368)
Johannes Gäßler committed
September 2, 2024
S
docker : fix missing binaries in full-cuda image (#9278)
slaren committed
August 28, 2024
S
docker : update CUDA images (#9213)
slaren committed
July 17, 2024
A
build : Fix docker build warnings (#8535) (#8537)
Al Mochkin committed
June 26, 2024
G
devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)
Georgi Gerganov committed
June 6, 2024
S
docker : add openmp lib (#7780)
slaren committed
May 30, 2024
J
Fixed painfully slow single process builds. (#7326)
JohnnyB committed
April 4, 2024
E
server: add cURL support to server Dockerfiles (#6474)
Ed Lepedus committed
March 26, 2024
S
cuda : rename build flag to LLAMA_CUDA (#6299)
slaren committed
December 29, 2023
C
python : add check-requirements.sh and GitHub workflow (#4585)
crasm committed
September 8, 2023
H
docker : add git to full-cuda.Dockerfile main-cuda.Dockerfile (#3044)
hongbo.mo committed
July 7, 2023
D
docker : add support for CUDA in docker (#1461)
dylan committed