Hundreds of models & providers. One command to find what runs on your hardware.
This report presents the forensic synthetic code analysis of AlexsJones/llmfit, a Rust project with 34,442 GitHub stars. SynthScan v2.0 examined 80,794 lines of code across 216 source files, recording 308 pattern matches distributed across 12 syntactic categories. The overall adjusted score of 8.0 places this repository in the Low AI signal band.
The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).
This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.
Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.
This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.
The scanner identified 308 distinct pattern matches across 12 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | llmfit-tui/src/tui_ui.rs | 5026 | // ── Live inference-bench view ───────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/display.rs | 487 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/display.rs | 489 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/display.rs | 922 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/display.rs | 924 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/main.rs | 1796 | // ── --status ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/main.rs | 1830 | // ── --clear ─────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/main.rs | 1840 | // ── fetch ───────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/main.rs | 2057 | // ── bench helpers ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/main.rs | 2769 | // ── main ─────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 1374 | // ── Restore persisted filters ──────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 2456 | // ── Benchmarks view ────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3341 | // ── Visual mode ────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3410 | // ── Select mode ───────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3476 | // ── Quant popup ───────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3510 | // ── RunMode popup ─────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3545 | // ── Params bucket popup ───────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3580 | // ── License popup ─────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3665 | // ── Hardware simulation ────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3819 | // ── Advanced Config Popup ────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 3850 | // ── Filter Popup ───────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 4821 | // ── Live inference-bench view ───────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 5278 | // ── matched GGUF source attribution (issue #569) ───────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 5278 | // ── matched GGUF source attribution (issue #569) ───────────────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 5365 | // ── available_download_providers MLX gating (issue #294) ───────── | COMMENT |
| MEDIUM | llmfit-tui/src/tui_app.rs | 5365 | // ── available_download_providers MLX gating (issue #294) ───────── | COMMENT |
| MEDIUM⚡ | scripts/scrape_hf_models.py | 1367 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | scripts/scrape_hf_models.py | 1369 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/scrape_hf_models.py | 1129 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/scrape_hf_models.py | 1131 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | scripts/verify_models.py | 42 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | scripts/verify_models.py | 44 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/verify_models.py | 69 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/verify_models.py | 71 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/verify_models.py | 116 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | scripts/verify_models.py | 118 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1108 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1110 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1204 | // ── Bandwidth-based estimation (preferred) ───────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1421 | // ── Fallback: fixed-constant approach ────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1499 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1501 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1770 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1772 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1837 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1839 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1910 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 1912 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2169 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2171 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2227 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2229 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2556 | // ── Estimate calibration against measured community benchmarks ────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2752 | // ── Usable context (issue #621) ───────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2752 | // ── Usable context (issue #621) ───────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2941 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2943 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2996 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 2998 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | llmfit-core/src/fit.rs | 3257 | // ──────────────────────────────────────────────────────────────────── | COMMENT |
| 130 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | llmfit-tui/src/main.rs | 41 | #[derive(clap::ValueEnum, Clone, Copy, Debug)] | COMMENT |
| LOW | llmfit-tui/src/main.rs | 141 | #[arg(long)] | COMMENT |
| LOW | llmfit-tui/src/main.rs | 161 | COMMENT | |
| LOW | llmfit-tui/src/main.rs | 261 | Claim { | COMMENT |
| LOW | llmfit-tui/src/main.rs | 661 | /// Fetch the latest LLM models from HuggingFace and update the local cache. | COMMENT |
| LOW | llmfit-tui/src/main.rs | 761 | host: String, | COMMENT |
| LOW | llmfit-tui/src/main.rs | 821 | /// Only test specific roles (comma-separated) | COMMENT |
| LOW | llmfit-tui/src/tui_app.rs | 361 | /// Failed — error message is displayed. | COMMENT |
| LOW | llmfit-core/src/analysis.rs | 201 | COMMENT | |
| LOW | llmfit-core/src/fit.rs | 1 | use crate::hardware::{GpuBackend, SystemSpecs}; | COMMENT |
| LOW | llmfit-core/src/fit.rs | 21 | /// Accounts for kernel launch overhead, KV-cache reads, memory controller inefficiency. | COMMENT |
| LOW | llmfit-core/src/fit.rs | 201 | /// Speed: estimated tokens/sec normalized to 0-100. | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1101 | } | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1121 | /// In practice, real throughput is ~50–70% of this ceiling due to kernel | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1201 | .unwrap_or_else(|| model.params_b()) | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1241 | // 1. MoeOffload mode: inactive experts in RAM, CPU reads active experts | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1281 | let mode_factor = config.run_mode_factors.for_run_mode(run_mode); | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1301 | // | COMMENT |
| LOW | llmfit-core/src/fit.rs | 1321 | // - OLMoE-1B-7B Q4_K_M (25% util, 8/64): penalty=1.0 → est 200, meas 258 (0.77x) | COMMENT |
| LOW | llmfit-core/src/fit.rs | 3621 | // | COMMENT |
| LOW | llmfit-core/src/fit.rs | 3801 | COMMENT | |
| LOW | llmfit-core/src/fit.rs | 3881 | active_experts: u32, | COMMENT |
| LOW | llmfit-core/src/models.rs | 501 | pub context_length: u32, | COMMENT |
| LOW | llmfit-core/src/models.rs | 521 | pub languages: Vec<String>, | COMMENT |
| LOW | llmfit-core/src/models.rs | 541 | /// attention. Only full attention layers have a context-scaled KV cache; | COMMENT |
| LOW | llmfit-core/src/models.rs | 561 | /// Model architecture string from HuggingFace config (e.g. "qwen2", "llama4", | COMMENT |
| LOW | llmfit-core/src/models.rs | 621 | } | COMMENT |
| LOW | llmfit-core/src/models.rs | 841 | COMMENT | |
| LOW | llmfit-core/src/models.rs | 921 | /// KV cache size in GB at the given context length and KV quant. | COMMENT |
| LOW | llmfit-core/src/models.rs | 1181 | } | COMMENT |
| LOW | llmfit-core/src/update.rs | 1 | //! Online model database updates via the HuggingFace Hub API. | COMMENT |
| LOW | llmfit-core/src/update.rs | 401 | head_dim: Option<u32>, | COMMENT |
| LOW | llmfit-core/src/plan.rs | 221 | let params = model | COMMENT |
| LOW | llmfit-core/src/benchmarks.rs | 121 | #[serde(default)] | COMMENT |
| LOW | llmfit-core/src/benchmarks.rs | 301 | params | COMMENT |
| LOW | llmfit-core/src/benchmarks.rs | 401 | /// all of which outrank the formula estimate. | COMMENT |
| LOW | llmfit-core/src/share.rs | 1 | //! Contribute benchmark results back to the project as a GitHub pull request. | COMMENT |
| LOW | llmfit-core/src/share.rs | 41 | /// requires no client secret, so shipping it in the binary is by design. | COMMENT |
| LOW | llmfit-core/src/share.rs | 321 | return Some(PathBuf::from(dir)); | COMMENT |
| LOW | llmfit-core/src/share.rs | 561 | /// already been submitted upstream and there was nothing to open a PR for. | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 601 | COMMENT | |
| LOW | llmfit-core/src/hardware.rs | 1101 | COMMENT | |
| LOW | llmfit-core/src/hardware.rs | 1161 | } | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 1321 | discrete | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 2541 | /// `HardwareInformation.MemorySize`, which may be a REG_BINARY blob or a | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 2681 | /// NVIDIA suffixes these adapters with "Laptop GPU"; earlier generations use | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 2701 | /// - Google, "Efficiently Scaling Transformer Inference" (arXiv:2211.05102) | COMMENT |
| LOW | llmfit-core/src/hardware.rs | 3121 | /// <https://docs.vllm.ai/en/latest/features/quantization/#supported-hardware> | COMMENT |
| LOW | llmfit-core/src/providers.rs | 321 | /// count of locally-installed models. Cloud-hosted models are skipped entirely: | COMMENT |
| LOW | llmfit-core/src/providers.rs | 861 | // llama.cpp provider (direct GGUF download from HuggingFace) | COMMENT |
| LOW | llmfit-core/src/providers.rs | 2601 | Some(lmstudio_gguf_resolve_url(repo_id, &filename)) | COMMENT |
| LOW | llmfit-core/src/providers.rs | 2641 | match url.split_once("/resolve/") { | COMMENT |
| LOW | llmfit-core/src/providers.rs | 2841 | /// vLLM accepts HF model names directly. | COMMENT |
| LOW | llmfit-core/src/providers.rs | 3001 | struct RamaLamaModel { | COMMENT |
| LOW | llmfit-core/src/providers.rs | 3261 | pub fn strip_gguf_quant_suffix(stem: &str) -> Option<String> { | COMMENT |
| LOW | llmfit-core/src/providers.rs | 3281 | let base = base.strip_suffix("-ud").unwrap_or(base); | COMMENT |
| LOW | llmfit-core/src/providers.rs | 3781 | COMMENT | |
| LOW | llmfit-core/src/providers.rs | 4141 | return installed_name.starts_with(&format!("{candidate}-")); | COMMENT |
| LOW | llmfit-core/src/bench.rs | 1 | //! LLM inference benchmarking against Ollama, vLLM, and MLX endpoints. | COMMENT |
| LOW | llmfit-core/src/claim.rs | 1 | //! Kubernetes DRA claim generation. | COMMENT |
| 1 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | llmfit-python/tests/test_llmfit.py | 15 | def test_find_llmfit_bin_raises_when_missing(monkeypatch: pytest.MonkeyPatch) -> None: | CODE |
| LOW | scripts/validate_generation_scoring.py | 15 | def qwen_minor_generation_from_name(name_lower: str) -> float | None: | CODE |
| LOW | scripts/test_preserve_catalog_metadata.py | 14 | def test_preserves_architecture_when_config_fetch_misses(): | CODE |
| LOW | scripts/test_preserve_catalog_metadata.py | 40 | def test_does_not_invent_heads_the_catalog_never_had(): | CODE |
| LOW | scripts/scrape_docker_models.py | 194 | def ollama_tag_to_docker_repo(ollama_tag: str) -> str: | CODE |
| LOW | scripts/scrape_hf_models.py | 494 | def preserve_existing_metadata(old_model: dict, fresh_model: dict) -> list[str]: | CODE |
| LOW | scripts/scrape_hf_models.py | 650 | def estimate_params_from_arch(config: dict | None) -> int | None: | CODE |
| LOW | scripts/scrape_hf_models.py | 1173 | def _model_gguf_repo_candidates(repo_id: str) -> list[tuple[str, str]]: | CODE |
| LOW | scripts/scrape_hf_models.py | 1444 | def _estimate_params_from_config(config: dict) -> int | None: | CODE |
| LOW | scripts/scrape_hf_models.py | 1805 | def drop_secret_bearing_models(models: list[dict]) -> tuple[list[dict], list[str]]: | CODE |
| LOW⚡ | scripts/test_api.py | 74 | def test_models_envelope_and_limit(base_url: str) -> None: | CODE |
| LOW⚡ | scripts/test_api.py | 83 | def test_top_endpoint_excludes_too_tight(base_url: str) -> None: | CODE |
| LOW⚡ | scripts/test_api.py | 91 | def test_filters_runtime_and_use_case(base_url: str) -> None: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | scripts/scrape_docker_models.py | 168 | print(f"Error fetching {url}: {e}", file=sys.stderr) | CODE |
| LOW | scripts/scrape_hf_models.py | 395 | except Exception as e: | CODE |
| LOW | scripts/scrape_hf_models.py | 783 | except Exception: | CODE |
| LOW | scripts/scrape_hf_models.py | 1219 | except Exception: | CODE |
| LOW | scripts/scrape_hf_models.py | 1266 | except Exception: | CODE |
| LOW | scripts/scrape_hf_models.py | 1628 | except Exception as e: | CODE |
| LOW | scripts/test_api.py | 183 | except Exception: | CODE |
| LOW | scripts/test_api.py | 263 | except Exception as exc: | CODE |
| LOW | scripts/test_api.py | 271 | except Exception: | CODE |
| LOW⚡ | scripts/verify_models.py | 38 | except Exception: | CODE |
| LOW | scripts/scrape_benchmarks.py | 103 | except Exception as e: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | scripts/validate_generation_scoring.py | 32 | CODE | |
| LOW | scripts/validate_generation_scoring.py | 188 | CODE | |
| LOW | scripts/validate_generation_scoring.py | 223 | CODE | |
| LOW | scripts/validate_generation_scoring.py | 260 | CODE | |
| LOW | scripts/scrape_hf_models.py | 888 | CODE | |
| LOW | scripts/scrape_hf_models.py | 918 | CODE | |
| LOW | scripts/scrape_hf_models.py | 1225 | CODE | |
| LOW | scripts/scrape_hf_models.py | 1290 | CODE | |
| LOW | scripts/scrape_hf_models.py | 1555 | CODE | |
| LOW | scripts/scrape_hf_models.py | 1710 | CODE | |
| LOW | scripts/scrape_hf_models.py | 1823 | CODE | |
| LOW | scripts/test_api.py | 235 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | llmfit-python/hatch_build.py | 27 | CODE | |
| LOW | llmfit-python/tests/test_llmfit.py | 3 | CODE | |
| LOW | llmfit-python/src/llmfit/__init__.py | 1 | CODE | |
| LOW | llmfit-python/src/llmfit/__main__.py | 1 | CODE | |
| LOW | scripts/validate_generation_scoring.py | 11 | CODE | |
| LOW | scripts/test_api.py | 13 | CODE | |
| LOW | scripts/validate_community_benchmarks.py | 25 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | install.sh | 171 | # Check if install dir is in PATH | COMMENT |
| LOW | scripts/update_models.sh | 27 | # Check if Python 3 is available | COMMENT |
| LOW | scripts/update_models.sh | 75 | # Check if cargo is available | COMMENT |
| LOW | scripts/scrape_hf_models.py | 615 | # Check if architecture is in known MoE configs | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | scripts/scrape_hf_models.py | 245 | # Embeddings (useful for RAG sizing) | COMMENT |
| MEDIUM⚡ | scripts/scrape_hf_models.py | 1376 | "feature-extraction", # Embedding models (useful for RAG sizing) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | docs/providers.md | 134 | export LMSTUDIO_API_KEY="your-api-key-here" | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | llmfit-desktop/ui/i18n.js | 252 | node.setAttribute('placeholder', t(node.getAttribute('data-i18n-placeholder'))); | CODE |
| LOW | llmfit-core/data/benchmarks.yaml | 974 | - { pattern: '"company"\\s*:\\s*"Acme Corp"', weight: 1, case_insensitive: true } | CODE |
| LOW | llmfit-core/data/benchmarks.yaml | 976 | - { pattern: '"phone"\\s*:\\s*"555-0123"', weight: 1 } | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | llmfit-core/src/fit.rs | 397 | // Step 1: pick the best available execution path | COMMENT |
| LOW⚡ | llmfit-core/src/fit.rs | 398 | // Step 2: score memory fit purely on headroom in that path's memory pool | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | llmfit-core/src/fit.rs | 397 | // Step 1: pick the best available execution path | COMMENT |
| LOW⚡ | llmfit-core/src/fit.rs | 398 | // Step 2: score memory fit purely on headroom in that path's memory pool | COMMENT |