The Path › Man pages › awswarm

awswarm(tool, public)

Run one model too big for any single GPU across a pool of small ones.

Name

awswarm — Run one model too big for any single GPU across a pool of small ones.

The problem it solves

A frontier MoE checkpoint (Kimi K3, ~1.56TB) fits no consumer card, and "rent a bigger box" stops being an option past a certain size. Splitting a model finely enough to run on heterogeneous, unreliable consumer GPUs -- some too small to hold even one full layer -- is a placement and scheduling problem with no shipped general answer. The money-losing failure mode is retrying a fleet acquisition that was never going to complete, because nothing scored the odds before spending on it.

Instead of trusting / you check

instead of trusting
that a model either fits your GPU or it doesn't run at all
you check
a placement plan and an acquisition-probability estimate before you spend on a run

Adopt it alone

Feed it one layer's shape and a pool of heterogeneous GPU specs and get back a sub-layer placement plan, plus the probability that plan actually assembles.

Install

install
pip install git+https://github.com/Aitherium/awswarm.git

Where it sits in the path

  • Not on the path yet — reference only.

See also

awnet · awrun · awdk

Links

Source on GitHub · Its own page

Generated 2026-09-14 00:48Z from the ecosystem registry. A field here that is wrong is wrong in the registry — fix it there and this page follows.

One estate, 8 doors

These projects are organs of the same system — the same identity plane, the same agent runtime, the same operational discipline. Follow any of them.

the osaitherium.comThe Living OS these four repos are cut from. Open, no login.pythonAither ADKBuild AI agent fleets — 3 lines, any backend, local or cloud.markdownawskillsPortable agent skills — self-contained procedures an agent loads on demand.markdownawknowledgeHow to run a coding agent so the result survives — the laws, with evidence.cudaaitherkvcacheNear-optimal KV cache quantization for LLM inference — sub-byte compression.powershellAitherZeroPowerShell 7+ automation framework — numbered, self-describing scripts.writingThe BlogHow all of it is actually built, measured and operated.pythonawrunA priority-aware queue and dispatcher for agentic runs and ad-hoc CI builds. It also judges whether the runner pool is big enough for the queue it is draining, and can ask a host to grow it -- reserving capacity is zero-sum, so a saturated pool needs more of it, not a different share of it.

The ecosystem this belongs to

Every Aitherium repository publishes an aither-manifest.json beside its page, and each surface reads all of them — so the network is browsable from any node in it.