Pytorch - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

ai maya

Aug 9

Model DNA, Analyzed: Verifying 'From-Scratch' LLM Claims with Architecture, Tokenizer, and CKA (PyTorch)

#ai #llm #machinelearning #pytorch

6 min read

Chaeyeon Mia Lee

Aug 6

ResKV: Recovering Evicted Token Contributions via Residual KV Cache — LongBench 32/32

#llm #machinelearning #performance #pytorch

6 min read

AS

Aug 2

Your quantized model got worse, and nothing told you

#flutter #dart #machinelearning #pytorch

5 min read

Oluwasegun Zyden

Jul 28

Demystifying Shape Mismatches: How to Debug and Fix Tensor Dimensions in PyTorch

#python #machinelearning #pytorch #tutorial

4 min read

Medha

Jul 25

I Trained a 6.4M-Parameter Transformer From Scratch to Talk About Recipes

#machinelearning #pytorch #llm #python

5 min read

Jul 22

RoPE: How 2D Rotations Solved Transformer Long-Context

#python #machinelearning #ai #pytorch

4 min read

Jul 22

Running Qwen3 Through the ExecuTorch MLX Delegate: Up to 4.52x Faster on M1 Max

#python #pytorch #llm #applesilicon

7 min read

Jul 21

Testing PyTorch 2.13 MPS FlexAttention on M1 Max: Up to 7.83x Faster for Sparse Attention

#python #pytorch #machinelearning #applesilicon

7 min read

Wesam Khallaf — Author of PyTorch From Ground Up

Jul 19

What Does `unsqueeze` Do in PyTorch? (And Why Your Model Keeps Asking For It)

#pytorch #python #beginners #deeplearning

7 min read

Wesam Khallaf — Author of PyTorch From Ground Up

Jul 16

PyTorch Broadcasting Explained: The 3 Rules (and the Silent Bug That Bites Everyone)

#python #pytorch #broadcasting #machinelearning

4 min read

Aug 5

GPU-Accelerating MSCRED with CUDA, im2col, GEMM, and a Custom PyTorch Extension

#pytorch #cuda #machinelearning #performance

11 min read

Jul 9

Debugging a Python "Memory Leak" That Was Actually a Measurement Bug (ru_maxrss vs VmRSS)

#python #debugging #pytorch #rag

4 min read

Jun 26

Classifier-free guidance above 7.5 oversaturated our product renders

#machinelearning #computervision #pytorch

4 min read

Jun 24

Using the channels-last memory format reduced the latency of our conversation backbone by 22%

#pytorch #computervision #machinelearning #mlops

4 min read

Jun 23

The SDXL VAE overflow that decoded black images in fp16

#pytorch #computervision #machinelearning #mlops

4 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.