RRepoGEO

REPOGEO REPORT · LITE

yassa9/qwen600

Default branch main · commit e35e37e5 · scanned 6/15/2026, 7:47:44 AM

GitHub: 557 stars · 48 forks

AI VISIBILITY SCORE
22 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
1 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface yassa9/qwen600, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README opening to emphasize 'suckless' and 'mini inference engine'

    Why:

    CURRENT
    While studying and practicing  CUDA & GPGPU, thought why not make an inference engine from scratch ? So, chose QWEN3-0.6B model, small model than can run smoothly on my `RTX 3050 8GB` VRAM.
My intention was (and still) to build educational program to learn about LLMs & transformers while maintaining practice in CUDA programming.
    COPY-PASTE FIX
    qwen600.cu is a static, suckless, single-batch CUDA-only mini inference engine for the Qwen3-0.6B instruct model, built from scratch for educational purposes and GPGPU practice. Inspired by projects like llama.cpp and llama2.c, it aims for minimalist design and high performance, claiming to be faster than llama.cpp by approximately 8.5% in tokens/sec.
  • hightopics#2
    Add 'suckless', 'from-scratch', and 'educational-project' to topics

    Why:

    CURRENT
    cuda, cuda-programming, gpu, llamacpp, llm, llm-inference, qwen, qwen3, transformer
    COPY-PASTE FIX
    cuda, cuda-programming, gpu, llamacpp, llm, llm-inference, qwen, qwen3, transformer, suckless, from-scratch, educational-project
  • mediumhomepage#3
    Add repository URL as homepage

    Why:

    COPY-PASTE FIX
    https://github.com/yassa9/qwen600

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface yassa9/qwen600
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
NVIDIA FasterTransformer
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. NVIDIA FasterTransformer · recommended 1×
  2. NVIDIA cuBLAS · recommended 1×
  3. NVIDIA cuDNN · recommended 1×
  4. NVIDIA TensorRT · recommended 1×
  5. OpenAI Triton · recommended 1×
  • CATEGORY QUERY
    Looking for a fast, low-level CUDA library for efficient transformer model inference.
    you: not recommended
    AI recommended (in order):
    1. NVIDIA FasterTransformer
    2. NVIDIA cuBLAS
    3. NVIDIA cuDNN
    4. NVIDIA TensorRT
    5. OpenAI Triton
    6. CUTLASS

    AI recommended 6 alternatives but never named yassa9/qwen600. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Need a lightweight, dependency-free LLM inference engine built purely with C++ and CUDA.
    you: not recommended
    AI recommended (in order):
    1. llama.cpp
    2. TensorRT-LLM
    3. ONNX Runtime
    4. TVM

    AI recommended 4 alternatives but never named yassa9/qwen600. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of yassa9/qwen600?
    pass
    AI did not name yassa9/qwen600 — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts yassa9/qwen600 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named yassa9/qwen600 explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo yassa9/qwen600 solve, and who is the primary audience?
    pass
    AI did not name yassa9/qwen600 — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of yassa9/qwen600. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/yassa9/qwen600.svg)](https://repogeo.com/en/r/yassa9/qwen600)
HTML
<a href="https://repogeo.com/en/r/yassa9/qwen600"><img src="https://repogeo.com/badge/yassa9/qwen600.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

yassa9/qwen600 — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite