Repository Analysis

deepseek-ai/DeepSeek-V3

13.8 Low AI signal View on GitHub

13.8

Adjusted Score

13.8

Raw Score

100%

Time Factor

2025-08-28

Last Push

103,643

Stars

Python

Language

2,023

Lines of Code

15

Files

8

Pattern Hits

2026-05-31

Scan Date

Score History

Severity Breakdown

CRITICAL 0HIGH 5MEDIUM 0LOW 3

Pattern Findings

8 matches across 2 categories. Click a row to expand file-level details.

Docstring Block Structure5 hits · 25 pts

Severity	File	Line	Snippet
HIGH	inference/kernel.py	90	Dequantizes the given weight tensor using the provided scale tensor. Args: x (torch.Tensor): The quant
HIGH	inference/model.py	108	Forward pass for parallel embedding layer. Args: x (torch.Tensor): Input tensor containing
HIGH	inference/model.py	132	Applies a linear transformation to the incoming data: y = xA^T + b. This function supports specialized implemen
HIGH	inference/fp8_cast_bf16.py	13	Converts FP8 weights to BF16 and saves the converted weights. This function reads FP8 weights from the specifi
HIGH	inference/fp8_cast_bf16.py	45	Retrieves a tensor from the cached safetensor files or loads it from disk if not cached. Args:

Deep Nesting3 hits · 3 pts

Severity	File	Line	Snippet
LOW	inference/generate.py	81
LOW	inference/convert.py	33
LOW	inference/fp8_cast_bf16.py	12