Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.

Dmytro-Khvedchuk/llm-inference-learning

https://github.com/Dmytro-Khvedchuk/llm-inference-learning · scanned 2026-06-17 01:26 UTC (1 month, 2 weeks ago)

10 raw signals (0 security + 10 graph)

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 1 month, 2 weeks ago · v2 · last Δ -14.9 (diff) · 10 actionable findings from 1 signal source. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all

All 30 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

LabelLayerStatusPath
main software healthy main.py:1
__init__ software healthy decode-loop-from-scratch/main.py:21
_top_k_modification software healthy decode-loop-from-scratch/main.py:28
_top_p_modification software healthy decode-loop-from-scratch/main.py:32
_temperature_application software healthy decode-loop-from-scratch/main.py:62
_prefill software healthy decode-loop-from-scratch/main.py:79
generate software healthy decode-loop-from-scratch/main.py:121
get_batch software healthy nano-gpt-karpathy/bigram.py:46
estimate_loss software healthy nano-gpt-karpathy/bigram.py:56
__init__ software healthy nano-gpt-karpathy/bigram.py:153
forward software dead nano-gpt-karpathy/bigram.py:162
generate software healthy nano-gpt-karpathy/bigram.py:185
main software healthy nano-gpt-karpathy/main.py:1

LabelLayerStatusPath
CLAUDE.md software healthy CLAUDE.md
README.md software healthy README.md
pyproject.toml software healthy pyproject.toml
main.py software healthy main.py
main.py software healthy decode-loop-from-scratch/main.py
bigram.py software healthy nano-gpt-karpathy/bigram.py
main.py software healthy nano-gpt-karpathy/main.py
CLAUDE.md quality warning CLAUDE.md

LabelLayerStatusPath
MyFirstLLMModel software healthy decode-loop-from-scratch/main.py:19
Head software healthy nano-gpt-karpathy/bigram.py:71
MultiHeadAttention software healthy nano-gpt-karpathy/bigram.py:108
FeedForward software healthy nano-gpt-karpathy/bigram.py:122
Block software healthy nano-gpt-karpathy/bigram.py:136
GenerativePretrainedTransformer software healthy nano-gpt-karpathy/bigram.py:152

LabelLayerStatusPath
decode-loop-from-scratch software healthy decode-loop-from-scratch
nano-gpt-karpathy software healthy nano-gpt-karpathy

LabelLayerStatusPath
Dmytro-Khvedchuk__llm-inference-learning software healthy /data/fable5_failed_archive/Dmytro-Khvedchuk__llm-inference…
For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.
For AI agents + API integrations
Email me when this repo regresses
Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.
API access

This page is publicly accessible at: https://repobility.com/scan/8518fafe-ba78-47de-91ab-e0fecaee6665/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/8518fafe-ba78-47de-91ab-e0fecaee6665/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.