Evgeny Kurnevsky e52aba537a

nix: allow to override rocm gpu targets (#10794) ...

This allows to reduce compile time when you are building for a single GPU.

2024-12-14 10:17:36 -08:00

..

nix

nix: allow to override rocm gpu targets (#10794)

2024-12-14 10:17:36 -08:00

cloud-v-pipeline

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

full-cuda.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

full-musa.Dockerfile

mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)

2024-11-26 17:00:41 +01:00

full-rocm.Dockerfile

Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)

2024-09-30 20:57:12 +02:00

full.Dockerfile

ggml : add predefined list of CPU backend variants to build (#10626)

2024-12-04 14:45:40 +01:00

llama-cli-cann.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-cli-cuda.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-cli-intel.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-cli-musa.Dockerfile

mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)

2024-11-26 17:00:41 +01:00

llama-cli-rocm.Dockerfile

Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)

2024-09-30 20:57:12 +02:00

llama-cli-vulkan.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-cli.Dockerfile

ggml : add predefined list of CPU backend variants to build (#10626)

2024-12-04 14:45:40 +01:00

llama-cpp-cuda.srpm.spec

devops : remove clblast + LLAMA_CUDA -> GGML_CUDA (#8139)

2024-06-26 19:32:07 +03:00

llama-cpp.srpm.spec

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

llama-server-cuda.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-server-intel.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-server-musa.Dockerfile

mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)

2024-11-26 17:00:41 +01:00

llama-server-rocm.Dockerfile

Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9641)

2024-09-30 20:57:12 +02:00

llama-server-vulkan.Dockerfile

docker: use GGML_NATIVE=OFF (#10368)

2024-11-18 00:21:53 +01:00

llama-server.Dockerfile

ggml : add predefined list of CPU backend variants to build (#10626)

2024-12-04 14:45:40 +01:00

tools.sh

fix: graceful shutdown for Docker images (#10815)

2024-12-13 18:23:50 +01:00