RRepoGEO

REPOGEO REPORT · LITE

rwitten/HighPerfLLMs2024

Default branch main · commit 183ee74a · scanned 6/11/2026, 8:13:37 PM

GitHub: 583 stars · 57 forks

AI VISIBILITY SCORE
17 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 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 rwitten/HighPerfLLMs2024, 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 the README H1 to explicitly state it's course material

    Why:

    CURRENT
    # High Performance LLMs 2024
Build a full scale, high-performance LLM from scratch in Jax! We cover training and inference, roofline analysis, compilation, sharding, profiling and more. You’ll leave the class comfortable in Jax and confident in your ability to design high-performance computing systems that reach near the physical limit.
    COPY-PASTE FIX
    # High Performance LLMs 2024: Course Materials
This repository contains the code and materials for the High Performance LLMs 2024 course. Learn to build a full-scale, high-performance LLM from scratch in Jax, covering training, inference, roofline analysis, compilation, sharding, and profiling. You’ll gain confidence in designing high-performance computing systems that reach near physical limits.
  • hightopics#2
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    jax, llm, high-performance-computing, machine-learning-optimization, deep-learning, training, inference, sharding, flash-attention, pallas, course-materials, education
  • highabout#3
    Add a concise description to the repository's 'About' section

    Why:

    COPY-PASTE FIX
    Code and materials for the High Performance LLMs 2024 course, focusing on building and optimizing LLMs in JAX for training and inference.

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 rwitten/HighPerfLLMs2024
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Flax
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Flax · recommended 2×
  2. Optax · recommended 2×
  3. JAX Core · recommended 1×
  4. Haiku · recommended 1×
  5. Equinox · recommended 1×
  • CATEGORY QUERY
    How to build efficient large language models using JAX for training and inference?
    you: not recommended
    AI recommended (in order):
    1. JAX Core
    2. Flax
    3. Haiku
    4. Equinox
    5. Optax
    6. Orbax
    7. JAX-Toolbox
    8. JAX-GPT
    9. TensorFlow Datasets (TFDS)
    10. Hugging Face Optimum
    11. FastAPI
    12. Flask
    13. ONNX
    14. ONNX Runtime
    15. TensorRT

    AI recommended 15 alternatives but never named rwitten/HighPerfLLMs2024. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking resources to optimize LLM performance, including sharding, attention schedules, and low-level JAX.
    you: not recommended
    AI recommended (in order):
    1. JAX
    2. Flax
    3. Optax
    4. Hugging Face Transformers

    AI recommended 4 alternatives but never named rwitten/HighPerfLLMs2024. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    fail

    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 rwitten/HighPerfLLMs2024?
    pass
    AI did not name rwitten/HighPerfLLMs2024 — 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 rwitten/HighPerfLLMs2024 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named rwitten/HighPerfLLMs2024 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 rwitten/HighPerfLLMs2024 solve, and who is the primary audience?
    pass
    AI did not name rwitten/HighPerfLLMs2024 — 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 rwitten/HighPerfLLMs2024. 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/rwitten/HighPerfLLMs2024.svg)](https://repogeo.com/en/r/rwitten/HighPerfLLMs2024)
HTML
<a href="https://repogeo.com/en/r/rwitten/HighPerfLLMs2024"><img src="https://repogeo.com/badge/rwitten/HighPerfLLMs2024.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

rwitten/HighPerfLLMs2024 — 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