RRepoGEO

REPOGEO REPORT · LITE

ztxz16/fastllm

Default branch master · commit e7082d66 · scanned 5/23/2026, 9:52:38 PM

GitHub: 4,689 stars · 463 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

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 ztxz16/fastllm, 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

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

OVERALL DIRECTION
  • highreadme#1
    Reposition the core value proposition to the top of the README

    Why:

    CURRENT
    # fastllm

| [快速开始](#快速开始) | [部署DeepSeek](docs/deepseek.md) | [部署Qwen3](docs/qwen3.md) | [版本日志](docs/version.md) | [English Document](README_EN.md)

# 引用说明

本项目参考了许多开源项目的代码和相关文章，具体请参考 [参考代码和文章](#参考代码和文章)

## 介绍

fastllm是c++实现自有算子替代Pytorch的高性能全功能大模型推理库，可以推理Qwen, Llama, Phi等稠密模型，以及DeepSeek, Qwen-moe等moe模型
    COPY-PASTE FIX
    # fastllm

fastllm是一个高性能、全功能的C++大模型推理库，不依赖PyTorch，并使用自有算子实现。它支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。

| [快速开始](#快速开始) | [部署DeepSeek](docs/deepseek.md) | [部署Qwen3](docs/qwen3.md) | [版本日志](docs/version.md) | [English Document](README_EN.md)

# 引用说明

本项目参考了许多开源项目的代码和相关文章，具体请参考 [参考代码和文章](#参考代码和文章)
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://github.com/ztxz16/fastllm

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 ztxz16/fastllm
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
bitsandbytes
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. bitsandbytes · recommended 1×
  2. GPTQ · recommended 1×
  3. AWQ · recommended 1×
  4. DistilBERT · recommended 1×
  5. TinyLlama · recommended 1×
  • CATEGORY QUERY
    How to achieve high-performance large language model inference on limited GPU memory?
    you: not recommended
    AI recommended (in order):
    1. bitsandbytes
    2. GPTQ
    3. AWQ
    4. DistilBERT
    5. TinyLlama
    6. Phi-2
    7. vLLM
    8. NVIDIA TensorRT
    9. OpenVINO
    10. Hugging Face Accelerate
    11. DeepSpeed
    12. FlashAttention-2
    13. PagedAttention

    AI recommended 13 alternatives but never named ztxz16/fastllm. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a C++ library for efficient LLM inference without PyTorch dependencies.
    you: not recommended
    AI recommended (in order):
    1. llama.cpp (ggerganov/llama.cpp)
    2. ONNX Runtime (microsoft/onnxruntime)
    3. TensorRT (NVIDIA/TensorRT)
    4. OpenVINO (openvinotoolkit/openvino)
    5. Apache TVM (apache/tvm)
    6. GGML (ggerganov/ggml)

    AI recommended 6 alternatives but never named ztxz16/fastllm. 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 ztxz16/fastllm?
    pass
    AI did not name ztxz16/fastllm — 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 ztxz16/fastllm in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ztxz16/fastllm 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 ztxz16/fastllm solve, and who is the primary audience?
    pass
    AI did not name ztxz16/fastllm — 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 ztxz16/fastllm. 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/ztxz16/fastllm.svg)](https://repogeo.com/en/r/ztxz16/fastllm)
HTML
<a href="https://repogeo.com/en/r/ztxz16/fastllm"><img src="https://repogeo.com/badge/ztxz16/fastllm.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ztxz16/fastllm — 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