Skip to content

Releases: BodhiSearch/llama.cpp

Base Images v2508242014-a7e6c5d

24 Aug 15:40
Compare
Choose a tag to compare

llama.cpp Base Images Release v2508242014-a7e6c5d

Released on: Invalid timestamp
Git commit: a7e6c5d

Available Images

All images include embedded version metadata and are ready for BodhiApp integration.

Build Results

CPU Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:cpu-2508242014-a7e6c5d

CUDA Runtime (Platform: linux/amd64) - Includes CPU fallback

docker pull ghcr.io/bodhisearch/llama.cpp:cuda-2508242014-a7e6c5d

ROCm Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:rocm-2508242014-a7e6c5d

Vulkan Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:vulkan-2508242014-a7e6c5d

Usage with BodhiApp

# Use as base image in BodhiApp
ARG BASE_VARIANT=cpu
FROM ghcr.io/bodhisearch/llama.cpp:${BASE_VARIANT}-2508242014-a7e6c5d AS runtime-base

# Your BodhiApp build continues...
# llama-server binary available at /app/bin/llama-server

Version Information

Each image contains version metadata accessible at runtime:

# Via Docker labels
docker inspect ghcr.io/bodhisearch/llama.cpp:cpu-2508242014-a7e6c5d

# Via version file in container
docker run --rm ghcr.io/bodhisearch/llama.cpp:cpu-2508242014-a7e6c5d cat /app/version.json

Changelog

  • Simplified Architecture: Focus on llama-server binary only
  • Embedded Metadata: Version, commit, timestamp info in images
  • Multi-platform Support: ARM64 support for CPU and Vulkan variants
  • BodhiApp Integration: Clean inheritance pattern with predictable paths
  • Tag-based Versioning: Timestamp-based versions for chronological ordering

Base Images v2508241952-a42c152

24 Aug 14:57
Compare
Choose a tag to compare

llama.cpp Base Images Release v2508241952-a42c152

Released on: Invalid timestamp
Git commit: a42c152

Available Images

All images include embedded version metadata and are ready for BodhiApp integration.

Build Results

CPU Runtime - Build failed

CUDA Runtime (Platform: linux/amd64) - Includes CPU fallback

docker pull ghcr.io/bodhisearch/llama.cpp:cuda-2508241952-a42c152

ROCm Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:rocm-2508241952-a42c152

Vulkan Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:vulkan-2508241952-a42c152

Usage with BodhiApp

# Use as base image in BodhiApp
ARG BASE_VARIANT=cpu
FROM ghcr.io/bodhisearch/llama.cpp:${BASE_VARIANT}-2508241952-a42c152 AS runtime-base

# Your BodhiApp build continues...
# llama-server binary available at /app/bin/llama-server

Version Information

Each image contains version metadata accessible at runtime:

# Via Docker labels
docker inspect ghcr.io/bodhisearch/llama.cpp:cpu-2508241952-a42c152

# Via version file in container
docker run --rm ghcr.io/bodhisearch/llama.cpp:cpu-2508241952-a42c152 cat /app/version.json

Changelog

  • Simplified Architecture: Focus on llama-server binary only
  • Embedded Metadata: Version, commit, timestamp info in images
  • Multi-platform Support: ARM64 support for CPU and Vulkan variants
  • BodhiApp Integration: Clean inheritance pattern with predictable paths
  • Tag-based Versioning: Timestamp-based versions for chronological ordering

Base Images v2508220624-f943ff5

22 Aug 01:29
Compare
Choose a tag to compare

llama.cpp Base Images Release v2508220624-f943ff5

Released on: 20250822-06-24 00:00
Git commit: f943ff5

Available Images

All images include embedded version metadata and are ready for BodhiApp integration.

Build Results

CPU Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:cpu-2508220624-f943ff5

CUDA Runtime (Platform: linux/amd64) - Includes CPU fallback

docker pull ghcr.io/bodhisearch/llama.cpp:cuda-2508220624-f943ff5

ROCm Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:rocm-2508220624-f943ff5

Vulkan Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:vulkan-2508220624-f943ff5

Usage with BodhiApp

# Use as base image in BodhiApp
ARG BASE_VARIANT=cpu
FROM ghcr.io/bodhisearch/llama.cpp:${BASE_VARIANT}-2508220624-f943ff5 AS runtime-base

# Your BodhiApp build continues...
# llama-server binary available at /app/bin/llama-server

Version Information

Each image contains version metadata accessible at runtime:

# Via Docker labels
docker inspect ghcr.io/bodhisearch/llama.cpp:cpu-2508220624-f943ff5

# Via version file in container
docker run --rm ghcr.io/bodhisearch/llama.cpp:cpu-2508220624-f943ff5 cat /app/version.json

Changelog

  • Simplified Architecture: Focus on llama-server binary only
  • Embedded Metadata: Version, commit, timestamp info in images
  • Multi-platform Support: ARM64 support for CPU and Vulkan variants
  • BodhiApp Integration: Clean inheritance pattern with predictable paths
  • Tag-based Versioning: Timestamp-based versions for chronological ordering

Base Images v2508210758-ab11f4c

21 Aug 03:08
Compare
Choose a tag to compare

llama.cpp Base Images Release v2508210758-ab11f4c

Released on: Invalid timestamp
Git commit: ab11f4c

Available Images

All images include embedded version metadata and are ready for BodhiApp integration.

Build Results

CPU Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:cpu-2508210758-ab11f4c

CUDA Runtime (Platform: linux/amd64) - Includes CPU fallback

docker pull ghcr.io/bodhisearch/llama.cpp:cuda-2508210758-ab11f4c

ROCm Runtime (Platform: linux/amd64)

docker pull ghcr.io/bodhisearch/llama.cpp:rocm-2508210758-ab11f4c

Vulkan Runtime - Build failed

Usage with BodhiApp

# Use as base image in BodhiApp
ARG BASE_VARIANT=cpu
FROM ghcr.io/bodhisearch/llama.cpp:${BASE_VARIANT}-2508210758-ab11f4c AS runtime-base

# Your BodhiApp build continues...
# llama-server binary available at /app/bin/llama-server

Version Information

Each image contains version metadata accessible at runtime:

# Via Docker labels
docker inspect ghcr.io/bodhisearch/llama.cpp:cpu-2508210758-ab11f4c

# Via version file in container
docker run --rm ghcr.io/bodhisearch/llama.cpp:cpu-2508210758-ab11f4c cat /app/version.json

Changelog

  • Simplified Architecture: Focus on llama-server binary only
  • Embedded Metadata: Version, commit, timestamp info in images
  • Multi-platform Support: ARM64 support for CPU and Vulkan variants
  • BodhiApp Integration: Clean inheritance pattern with predictable paths
  • Tag-based Versioning: Timestamp-based versions for chronological ordering

server-bodhiapp_20250820-b6185-3129111

20 Aug 16:27
Compare
Choose a tag to compare
[Amir] base image workflow

server-bodhiapp_20250817-b6184-910cb5c

20 Aug 13:15
Compare
Choose a tag to compare
[Amir] changes for bodhiapp

- having git workflows to build binaries for supported platforms
- added ubuntu-arm64 platform to build

server-base-images-v2508202152-3129111-b6185-3129111

server-b6185

20 Aug 16:27
Compare
Choose a tag to compare
[Amir] base image workflow

server-bodhiapp_20250817-b6184-fb7b493

18 Aug 07:42
Compare
Choose a tag to compare
[Amir] changes for bodhiapp

- having git workflows to build binaries for supported platforms
- added ubuntu-arm64 platform to build

server-bodhiapp_20250817-b6184-6f884f1

17 Aug 06:26
Compare
Choose a tag to compare
[Amir] changes for bodhiapp

- having git workflows to build binaries for supported platforms