{ "checker": { "claims": [ { "claim": "One-shot chat with the edge0 CLI answers a prompt", "command": " chat edge0-8b --prompt 'Explain streaming inference in one sentence.' --max-new 48", "evidence": "Streaming inference is the technique of processing and generating responses from an AI model in real-time as data is being streamed, rather than waiting for a complete input to be processed before output begins.\n# 37 tokens in 92.297s\n", "expected": "A one-sentence answer about streaming inference is printed", "input": "edge0-8b tier (edge0-35b not used: 23 GB checkpoint, 3 GB RAM guest) with the same prompt", "kind": "claim", "outcome": "Real input produced the expected result: Streaming inference", "returncode": 0, "source": "edge0 chat edge0-35b --prompt \"Explain streaming inference in one sentence.\"", "source_checked": true, "source_file": "README.md", "verdict": "yes" } ], "cycle_checks": [ { "claim": "Scheduled or looping main behavior", "command": "", "evidence": "Entry points inspected: edge0 CLI (demo/chat/serve/models) and python/src/edge0/server/app.py. The only while-True loop (app.py:208) is a per-request streaming queue consumer, not a schedule. No cron, --once, --now, scheduler or webhook trigger exists in the product; serve is a long-running request server, run on demand.", "expected": "identify the product trigger", "input": "source inspection", "kind": "cycle", "outcome": "Entry points inspected: edge0 CLI (demo/chat/serve/models) and python/src/edge0/server/app.py. The only while-True loop (app.py:208) is a per-request streaming queue consumer, not a schedule. No cron, --once, --now, scheduler or webhook trigger exists in the product; serve is a long-running request server, run on demand.", "source": "repository entry points", "verdict": "yes" } ], "details": { "argv": [ "", "chat", "edge0-8b", "--prompt", "Explain streaming inference in one sentence.", "--max-new", "48" ], "kind": "cli", "needs_browser": false, "needs_credentials": false, "returncode": 0, "scope": "product operation", "stderr": "# 33 tokens in 83.553s", "stdout": "[lora] applied=153 not_found=0 skipped=0 scale=2.0\n[edge0-8b] prerouter installed: 16 heads, start=7, K=8\n[edge0-8b] built in 0.9s\nStreaming inference is the technique of processing and sending model responses in real-time as they are generated, rather than waiting for a full computation to complete before outputting results.", "working": true }, "evidence_strength": "readme_checked", "example_checks": [ { "claim": "Repository unit tests run offline (no real weights)", "command": " -q", "deferred": false, "evidence": "........................................................................ [ 39%]\n.......................................................ss..s............ [ 78%]\n....................................... [100%]\n180 passed, 3 skipped, 4 deselected in 16.15s", "expected": "all collected tests pass", "input": "pytest -q in python/ venv", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "python/README.md", "verdict": "yes" } ], "status": "PASS" }, "deviations": [ "python3.12 -m venv failed: ensurepip not available. Fixed with sudo apt-get install python3.12-venv, then reran the README install command unchanged.", "pip install -e '.[dev,fetch]' succeeded but `edge0` failed at import: libmlx.so missing. The mlx 0.30.6 Linux wheel does not include the CPU library. Installed mlx-cpu==0.30.6 (same version, not in README/pyproject) into the venv.", "First chat failed: MLX CPU JIT needs g++, which was missing. Fixed with sudo apt-get install g++.", "Second chat failed: GCC 13 rejects MLX's generated CPU kernel (redeclaration of built-in type '_Float32'). Worked around by a PATH-first g++ wrapper at that adds -fpermissive. This is an environment-only change outside the repo; no product source was edited. The probe and claim env set PATH to use this wrapper.", "Chat generation on CPU is slow: about 90 s for 37-39 tokens with edge0-8b.", "Cycles: none. The product has no cron, --once, --now, scheduler or webhook trigger; the while-True loop in server/app.py is a streaming queue consumer. cycles.json is detected:false.", "README tier example used edge0-35b; the claim uses edge0-8b because 35b is too large for this guest. Model checkpoint directory python/models (4.3 GB) and python/.venv are left in the checkout." ], "fault_owner": null, "main_blocker": null, "operation": "Run a one-shot generation with the edge0 CLI: `edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\"`, using the downloaded edge0-8b checkpoint, on Linux x86_64 CPU.", "operation_scope": "Linux x86_64 guest (Ubuntu 24.04, 2 vCPU, 3 GB RAM), CPU-only MLX build, edge0-8b tier only. The README documents the Python framework as macOS / Apple Silicon only, so this is an unsupported platform that works with the deviations below. edge0-35b (23 GB, needs more RAM) was not run. Unit tests (pytest) and one chat generation were replayed and passed.", "outcome": "working", "plain_failure": null, "steps": [ "git init; git remote add origin https://github.com/Edge0-AI/Edge0; git fetch --depth 1 origin e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5; git reset --mixed FETCH_HEAD", "cd python && python3.12 -m venv .venv && .venv/bin/pip install -e '.[dev,fetch]'", "export EDGE0_8B_MODEL=$PWD/models/edge0-8b; .venv/bin/python scripts/fetch_models.py --tier edge0-8b --target-dir models", "edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\" --max-new 48", "pytest (unit tests, in python/ venv)" ], "stuck_step": null, "suggested_fix": "Documentation/product: state Linux support status explicitly (the README says macOS Apple Silicon only). For Linux CPU, the mlx-cpu package and a -fpermissive or newer-GCC build of the MLX CPU JIT are needed; the README should list these prerequisites (python3.12-venv, g++, mlx-cpu) and the GCC 13 incompatibility should be reported upstream to MLX." }