mesh-llm
mesh-llm 0.80.0 · pkgs/by-name/me/mesh-llm/package.nix
Health
Risk
risk 0 ok
Version
Update bot
no attempt logged · not in the queue
Channels
Hydra, nixos-26.05
Advisories
none open
Packaging
meta complete
Packagewhat each field means
Description
Pool spare GPU capacity to run LLMs at larger scale
Long description
MeshLLM pools the GPUs of several machines to serve large language
models through an OpenAI-compatible API and a web console. By default it
bundles the Metal runtime on macOS and the CPU runtime on Linux; GPU
backends on Linux are enabled with the nixpkgs settings `cudaSupport`
(unfree) or `rocmSupport`, or Vulkan by overriding skippy-native-runtime
with `vulkanSupport = true`.
License
Platforms
3 platforms: Linux, Darwin · not on
patternMain program
mesh-llmSource provenance
not set: built from source
Outputs
outStatus
not broken, not insecure, free
Maintainers
Version bumps 0
all open bumpsNone open.
Pull requests 4
mesh-llmPlugins.{metrics,flash-moe,blackboard,agents}: init draft
#583566 by kleinbem · opened 2w ago · checks pass
mesh-llmPlugins.openai-endpoint, mesh-llmPlugins.capsules: init; nixos/mesh-llm: add plugins option draft
#583565 by kleinbem · opened 2w ago · checks pass
Closed or merged in the last 60 days 1
Issues 0
None open.