| .. |
|
nix
|
e52aba537a
nix: allow to override rocm gpu targets (#10794)
|
il y a 1 an |
|
cloud-v-pipeline
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
il y a 1 an |
|
full-cuda.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
full-musa.Dockerfile
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
il y a 1 an |
|
full-rocm.Dockerfile
|
6f1d9d71f4
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)
|
il y a 1 an |
|
full.Dockerfile
|
59f4db1088
ggml : add predefined list of CPU backend variants to build (#10626)
|
il y a 1 an |
|
llama-cli-cann.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-cli-cuda.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-cli-intel.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-cli-musa.Dockerfile
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
il y a 1 an |
|
llama-cli-rocm.Dockerfile
|
6f1d9d71f4
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)
|
il y a 1 an |
|
llama-cli-vulkan.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-cli.Dockerfile
|
59f4db1088
ggml : add predefined list of CPU backend variants to build (#10626)
|
il y a 1 an |
|
llama-cpp-cuda.srpm.spec
|
0e814dfc42
devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)
|
il y a 1 an |
|
llama-cpp.srpm.spec
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
il y a 1 an |
|
llama-server-cuda.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-server-intel.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-server-musa.Dockerfile
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
il y a 1 an |
|
llama-server-rocm.Dockerfile
|
6f1d9d71f4
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)
|
il y a 1 an |
|
llama-server-vulkan.Dockerfile
|
75207b3a88
docker: use GGML_NATIVE=OFF (#10368)
|
il y a 1 an |
|
llama-server.Dockerfile
|
59f4db1088
ggml : add predefined list of CPU backend variants to build (#10626)
|
il y a 1 an |
|
tools.sh
|
11e07fd63b
fix: graceful shutdown for Docker images (#10815)
|
il y a 1 an |
Evgeny Kurnevsky
e52aba537a
nix: allow to override rocm gpu targets (#10794)