wylab/llama-swap
1
0
Fork 1
mirror of https://github.com/mostlygeek/llama-swap.git synced 2026-09-07 16:37:22 +02:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity
585 Commits 3 Branches 200 Tags
v254
Commit Graph
7 Commits
Author SHA1 Message Date
Benson WongandGitHub 6c7f9587dd docker/unified: add cuda13 with multi-platform support for arm64 (#1093) 
Key changes: 

- add cuda13 container for Ampere to Blackwell GPUs
- support DGX Spark (GB10) with arm64 cuda 13 manifests
- enable ik_llama on vulkan container 
- map `LLAMA_SWAP_*` env vars to llama-server CLI flags with backwards support
- refactor GHA/docker build to accept variants

closes: #905, #1066
supercedes: PR #841, PR #1084
 2026-09-05 09:22:52 -07:00
DamirandGitHub 7a14664d98 docker/unified: make CUDA version and architectures configurable (#1072) 
- Add option to specify CUDA version and architectures during image
building. If not provided, it should behave just like now.
- Include Stable Diffusion UI in SD binaries. 
- Fix ik_llama.cpp build for arm64 architecture:
https://github.com/ikawrakow/ik_llama.cpp/issues/1684.
 2026-08-31 16:09:17 -07:00
Benson WongandGitHub e31a1adee4 Split Docker build into per-project stages for CI (#1071) 
Big refactor to split the build stages for the unified container to be built in parallel. 

- parallel building of binaries to speed up full container build (~6+hr to 1.5hr) 
- split cuda and vulkan pipelines to be independent (vulkan is much faster)
- establish pattern for building building binaries for final image (easier to add new resources)
- use llama-swap-build for build containers to avoid untagged clean up script

Fixes: #1069
 2026-08-30 11:57:20 -07:00
Benson WongandGitHub 6ffd67fdf2 internal/reference: add indexed docs and /api/tools endpoints (#1054)
Validate JSON Schema / validate-schema (push) Successful in 37s
Details
Build Containers / build-and-push (cpu) (push) Failing after 39s
Details
Build Containers / build-and-push (cuda) (push) Failing after 30s
Details
Build Containers / build-and-push (cuda13) (push) Failing after 29s
Details
Build Containers / build-and-push (intel) (push) Failing after 30s
Details
Build Containers / build-and-push (musa) (push) Failing after 29s
Details
Build Containers / build-and-push (rocm) (push) Failing after 40s
Details
Build Containers / build-and-push (vulkan) (push) Failing after 32s
Details
Build Containers / delete-untagged-containers (push) Skipped
Details
Linux CI / run-tests (push) Failing after 2m33s
Details
UI Tests / run-tests (push) Successful in 43s
Details
Windows CI / run-tests (push) Canceled after 0s
Details 
Add an Docs agent to the playground that can help the user with more
advanced configuration.

- add mcp 2026-07-28 (stateless mcp) framework 
- add MCP tools for doc search and config search
- add initial set of guides for key topics
- add Docs to the Playground
- removed out of data documentation and plans
 2026-08-29 23:43:09 -07:00
Benson WongandGitHub 23c28febf1 docker/unified: build audio.cpp as a deployment build (#1023) 2026-08-18 20:12:17 -07:00
Benson WongandGitHub 60226b6377 docker/unified: add llama-bench, vllm-wrapper, audio.cpp (#1011) 
New binaries included in the unified container: 

- add llama-bench
- add vllm-wrapper
- add audio.cpp

fixes: #714, #985, #998,
 2026-08-14 08:45:40 -07:00
Benson WongandGitHub 916d13f5bd .github/workflows,docker/unified: add cuda based unified container (#597) 
Add Docker build scripts for a unified cuda docker container with llama-server, stable-diffusion.cpp, whisper.cpp.
 2026-03-22 21:11:54 +09:00