Cuda - DEV Community

Skip to content

DEV Community

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

xbill for Google Developer Experts

Oct 27

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

#gemma #llamacpp #aws #cuda

10 min read

xbill for AWS Community Builders

Oct 27

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

#gemma #llamacpp #aws #cuda

10 min read

Oct 27

Know Rust? Learn CUDA by Solving GPU Challenges

#rust #cuda #gpu

4 min read

Runcrate

Oct 26

How long until a rented GPU runs CUDA? Launch to first matmul on six GPU types, timed

#gpu #cuda #pytorch #devops

5 min read

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

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

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

xbill for Google Developer Experts

Oct 20

A Dense 31B on an 8 GB GPU: Gemma 4 31B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking

10 min read

Includes a tricky broadcast K/V debugging story

xbill for Google Developer Experts

Oct 24

Gemma 4 on a 4 GB GPU in Plain PyTorch: From Out of Memory to Faster Than llama.cpp

#gemma #pytorch #cuda #quantization

13 min read

xbill for Google Developer Experts

Oct 18

Can a QAT 12B Fit an 8 GB GPU? Gemma 4 12B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking

15 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.