Cuda - DEV Community

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

MindAllik

Nov 11

I built a free Windows (UEFI) & Linux GUI to unlock RTX 40/30/20 Tensor Cores (2.01x FP16/BF16/FP8 on my RTX 4070 Ti)

#machinelearning #opensource #cuda #python

3 min read

SparkLLM

Nov 11

Same A40, same Spark file: inside cortiq’s new CUDA path

#ai #opensource #cuda #machinelearning

4 min read

Hisa Araki

Nov 8

Splitting Network Paths with Two NICs to Get CUDA Working on RTX 5060 under WSL2 on Windows 11

#linux #cuda #nvidia

4 min read

Checo Cadena

Nov 6

I had an AI agent port Karpathy's GPT-2 trainer from CUDA to SYCL, and made it prove every step

#cuda #gpu #ai #opensource

4 min read

Masahiro Morino

Nov 1

How Does Rust Code Run on a GPU? Tracing cuda-oxide and PTX

#rust #gpu #cuda #computerscience

10 min read

Arunav Pathak

Oct 22

Project EREN: My Journey to Building a CUDA-Powered LLM Inference Engine

#ai #llm #cuda #opensource

4 min read

jamilxt

Oct 21

TorchTPU vs CUDA: Can Native PyTorch Make Google TPUs Easier to Use?

#pytorch #tpu #cuda #ai

8 min read

Sumit Sodhi

Nov 3

Qwen3.8-Flash-Next (125B) on an RTX 3060 12 GB with 30 GB RAM: 50-70 tok/s

#llm #opensource #cuda #machinelearning

3 min read

Hacks.gr

Oct 19

Amazon: New TorchNeuron tool challenges Nvidia's dominance

#torchneuron #pytorch #trainium #cuda

2 min read

Helgard

Oct 17

Running NVIDIA's new 120B Nemotron-3.5-Super on an 8 GB GPU — skipping the zeros, and finding the real bottleneck

#ai #llm #cuda #python

7 min read

Hardware differences subtly alter benchmark grades

xbill for Google Developer Experts

Nov 6

One Word, Two GPUs: Why Gemma 4 Answers the Same Question Differently on a Laptop and a Tesla T4

#gemma #llamacpp #cuda #nvidia

12 min read

Musharaf Khan Pathan

Oct 10

I wrote 21 CUDA kernels on a free GPU. Here's what the profiler taught me.

#cuda #gpu #performance #cpp

5 min read

aivrar

Oct 9

Running vLLM natively on Windows

#vllm #windows #cuda #llm

6 min read

Helgard

Oct 3

Running the 510 GB DeepSeek-V4.1-Flash on an 8 GB GPU — and three bugs that never raise an error

#ai #llm #cuda #python

8 min read

Helgard

Oct 3

Running a 133 GB MoE model on an 8 GB GPU at 11 tokens/s by streaming experts from NVMe

#ai #llm #cuda #python

6 min read

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