Commit graph

8 commits

Author SHA1 Message Date
c67ce181c2 feat(distribution): add n3 observability introspectors
Relay/subprocess/registry introspectors, build-time dep-version + git-sha, postproc
RTT/inference render, new swactor-iroh-relay binary; dashboard replay-viewer, sim SWIM
tuning report + repro tests, N3 postmortem docs.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-25 22:19:06 +04:00
f7bd49c4b8 feat(sim): add swim host adapter and network model
Restructures the crate to the SIM_SPEC six-component model (engine, network, host,
bundle, evaluator, scenario) and relocates SIM_SPEC.md into the crate. Adds the SWIM
host adapter wrapping production distribution::swim::SwimNode, the swim codec, a
virtual network model, the scenario loader, an assertion evaluator, deterministic RNG,
property-based tests, and reproduction/smoke/topology scenario TOMLs; drops the
detector/divergence/lint/postproc/spec/runtime modules and prior spec docs.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-24 13:05:11 +04:00
00270a4059 docs(sim): add determinism scope to SIM_SPEC
Appends section 7.7 clarifying that the determinism contracts bind only the
simulator's own components: hidden entropy inside a wrapped production dependency
(allocator state, HashMap RandomState, process-local entropy) is out of scope, and
property tests comparing two independently-allocated wrapped state machines should
not be written.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-22 15:06:07 +04:00
f1f98e9f7d spec: add behavioral test subsections to SIM_SPEC.md
Six per-component property-test subsections (§4.10 engine, §5.8 network,
§6.4 hosting, §8.4 scenario loader, §9.6 bundle writer, §10.5 assertion
evaluator) written in property-language form. Each names the property the
component must have; how the property is verified is the test author's
call.

These were drafted in conversation but never committed, causing the
boundary check to flag SIM_SPEC.md on iteration 1 of the implementation
loop. Committing now puts them at HEAD so future loop iterations diff
cleanly.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-22 08:08:01 +00:00
28bc3c0c95 chore: bump iroh to 0.98, drop vendored patch
Upgrades iroh/iroh-relay across datastore, distribution, node, and integration,
adapts iroh_driver to the new Endpoint::builder(Minimal).relay_mode(...) API, and
removes the vendored ed25519-dalek patch now that 0.98 resolves the upstream compile
errors. Adds the SIM_SPEC.md simulator MVP spec under pipeline-parallel-inference.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-22 11:06:58 +04:00
1f8a67231c feat(sim): rebuild around discrete-event engine
Replaces the generic SimNode/gossip/dashboard framework with a virtual-time
discrete-event engine (priority queue ordered by time/node/fiber/seq), a TOML spec
parser, bundle writer, replay, divergence detector, lint, and postproc, plus the
parity-bar test harness with fixtures and xtask parity-lock tooling. Rewrites
transport identity/crypto and adds the SPEC/TESTING_SPEC/OBSERVABILITY/NORTH_STAR docs.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-21 23:48:02 +04:00
b23f82e9a9 feat(distribution): add diagnostics subsystem
Structured observability for the iroh/SWIM layer: Aggregator, typed Event/Snapshot
types, Sink (NoopSink default), ProbeScheduler, process stats, and host/iroh/swim
introspection, plus the swactor-diag-collector, -postproc, and -iroh-relay binaries
that assemble and render per-run bundles. Generalizes the pipeline-parallel-inference
example to N stages and adds the topology-planner spec.


Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-20 11:41:30 +04:00
a2ec548134 feat: two-node pipeline parallel example
Extend the single-GPU example into a two-node pipeline-parallel run that splits llama3.2:1b across two rented vast.ai GPUs and closes the autoregressive decode loop over iroh.

- topology: add linear-chain helpers where each stage derives its neighbours locally from `STAGE`/`NUM_STAGES`, registering `pp-entry`/`pp-exit`/`pp-stage-{i}` SWIM names
- messages: add `StageActivation` (bf16 hidden-state hand-off carrying position/seq_len/is_prefill) and `NextToken` (sampled-token feedback with a `done` flag) that close the autoregressive loop between stage 0 and stage 1
- stage_actor: add `Stage0Actor` (tokenize -> embed_and_forward -> prefill activation; decode_step on each NextToken) and `Stage1Actor` (forward_and_sample -> NextToken back; emit InferenceResponse on EOS/max_tokens)
- vastai: fork the client and add `create_pipeline_instances` (rents one instance per stage, threading `STAGE`/`NUM_STAGES`, best-effort destroys on partial failure) and `destroy_all_instances`
- pp_tinygrad_worker.py: per-stage worker slicing `model.blk[start:end]` in stub and real (GGUF) modes, plus new `pp_gpu_node`/`pp_smoke_run` binaries and ROADMAP/SPEC/TEST_SPEC docs
- reuse: build on the single-GPU example's iroh transport and process bridge unchanged; add actor/codec/topology/integration test suites

Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-16 09:49:43 +04:00