swactor/examples/single-gpu-inference/echo_worker.py
Zachery Aaron Shores-Chmielewski 8e4987618f feat: Working vastai single-node deployment for LLM inference
Add a complete single-GPU distributed-inference example that rents a vast.ai GPU, boots a worker container, and runs a prompt end-to-end over iroh/SWIM.

- examples/single-gpu-inference: add the `single_gpu_inference` orchestrator binary that starts a local iroh node, waits for the remote gpu-node to register the `"inference"` SWIM name, then sends an `InferenceRequest` and prints the response
- examples/single-gpu-inference: add the `gpu_node` binary that joins the cluster via `SEED_ADDR`, spawns an `InferenceActor` over `tinygrad_worker.py`, and registers the `"inference"` bridge
- inference_actor: bridge swactor messaging to a Python child process via stdin/stdout JSON, with `ProcessBridge`/`RequestBridge` adapters that satisfy the single-`Incoming` actor constraint
- iroh_transport: add `IrohActorTransport` that sends `WireEnvelope`s over iroh QUIC uni-streams (connection-cached against early close), plus wire encode/decode and an inbound drain helper
- vastai: add a vast.ai REST client (`find_offer` with reliability/cuda/geo filters excluding CN, `create_instance`, `wait_for_running`, `destroy_instance`) parameterised by a mockable `base_url`
- worker/docs/tests: ship `tinygrad_worker.py`/`echo_worker.py` (newline-JSON, `--stub`/`--model` defaulting to llama3.2:1b), a Dockerfile, Makefile, SPEC, and actor/codec/cluster/integration/vastai test suites

Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
2026-05-14 11:19:28 +04:00

16 lines
541 B
Python

#!/usr/bin/env python3
"""Stub worker for testing. Same JSON protocol as tinygrad_worker.py."""
import json, os, sys
print(json.dumps({"status": "ready", "pid": os.getpid()}), flush=True)
for line in sys.stdin:
line = line.strip()
if not line:
continue
try:
req = json.loads(line)
if req.get("prompt") == "__crash__":
os._exit(1)
print(json.dumps({"response": f"echo: {req['prompt']}"}), flush=True)
except Exception as e:
print(json.dumps({"error": str(e)}), flush=True)