No description
Zachery Aaron Shores-Chmielewski
fdc3c9663f
Get the multinode pipeline-parallel prompt loop actually running locally by supporting both tinygrad LLM backends and switching the Docker scenario to direct addressing. - tinygrad_worker.py (load_pipeline_stage_model): try the modern tinygrad.llm gguf/model modules first and fall back to the legacy tinygrad.apps.llm TransformerBlock on ModuleNotFoundError, with PipelineStageTinygradModel constructing blocks positionally when no TransformerConfig exists - tinygrad_worker.py (load_weights): drop the Transformer.from_gguf whole-model branch and its TinygradAppsLlmPartialStageUnsupported fatal, so partial pipeline stages build through load_pipeline_stage_model on either backend - xtask (MultinodeDocker): stop forcing --relay-mode default --endpoint-addr-mask relay-only, so the scenario runs over the Docker network with full/direct addresses - xtask (dump-log facts): rename relay_masked_* facts to docker_*, assert multiple workers join the coordinator via direct addresses (direct_addr_count > 0), and relax the benchmark report to skip the ensure_worker_binary span for the Docker scenario Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com> |
||
|---|---|---|
| .cargo | ||
| apps/mvp-node | ||
| crates | ||
| src | ||
| tests | ||
| tools/vastai | ||
| xtask | ||
| .dockerignore | ||
| .gitignore | ||
| Cargo.lock | ||
| Cargo.toml | ||
| README.md | ||
swactor
Minimal actor runtime for Rust. One trait, one message type.
Single-threaded (tick()) or multi-threaded (run()).
Description
Core runtime is src/. Actors implement ActorInterface (in actor.rs),
interact through Ctx (in runtime.rs), and run on worker threads (worker.rs).
crates/ builds upward: std adds OTP patterns (supervision, monitoring, groups),
distribution adds clustering, everything else composes from there.
Dev commands
cargo xtask --help for the basic test command.
Testing
cargo check --workspace
cargo xtask test