Pytorch

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

Ingero Team

May 28

Tracing torch.cuda.empty_cache() on an RTX 4090 - Where Do the 53 MB Go?

#gpu #cuda #pytorch #debugging

5 min read

Marco Rinaldi

May 28

QAT vs PTQ on our edge vision model: 6 months of A/B data

#machinelearning #computervision #mlops #pytorch

4 min read

Marco Rinaldi

May 29

Structured channel pruning got our detector under 12ms on a Jetson

#computervision #pytorch #machinelearning #mlops

4 min read

Marcus Chen

May 29

Serving 40 LoRA adapters on one base model: the throughput we got

#machinelearning #llm #pytorch #mlops

4 min read

Elise Moreau

May 29

torch.compile recompiled our SDXL UNet 38 times in production

#pytorch #machinelearning #computervision #mlops

4 min read

Marcus Chen

May 27

LLM-as-judge variance broke our DPO training signal for 3 weeks

#machinelearning #mlops #llm #pytorch

4 min read

Elise Moreau

May 27

The bf16 grad accumulator that killed our SDXL LoRA training

#machinelearning #pytorch #mlops #computervision

4 min read

Aditya Mehra

May 26

I Built a Diagnostic Toolkit for PyTorch Because I Was Tired of Guessing Why Models Fail

#pytorch #python #machinelearning #opensource

2 min read

Alan West

May 24

Why Your PyTorch Training Crawls on a Beefy GPU (And How to Fix It)

#pytorch #performance #machinelearning #gpu

5 min read

Marco Rinaldi

May 28

VLM-scored calibration sets for INT8 quantisation, routed through Bifrost

#machinelearning #mlops #computervision #pytorch

4 min read

Marcus Chen

May 26

Prefix caching in vLLM under multi-tenant agent traffic

#llm #mlops #infrastructure #pytorch

4 min read

Elise Moreau

May 19

Why your diffusion model is slow at batch size 1 (and what actually helps)

#machinelearning #pytorch #computervision #mlops

4 min read

Pooja Kiran

May 19

Your PyTorch Model File Can Execute Arbitrary Code — Here's How I Built a Scanner to Detect It

#security #python #machinelearning #pytorch

3 min read

Marco Rinaldi

May 27

Distilling SAM 2 into a 6MB student for industrial inspection

#computervision #machinelearning #pytorch #mlops

4 min read

shinji shimizu

May 26

My high-res image-to-video kept OOMing — turns out I was decoding outside no_grad

#pytorch #ai #machinelearning #python

4 min read

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

DEV Community

# pytorch

Tracing torch.cuda.empty_cache() on an RTX 4090 - Where Do the 53 MB Go?

QAT vs PTQ on our edge vision model: 6 months of A/B data

Structured channel pruning got our detector under 12ms on a Jetson

Serving 40 LoRA adapters on one base model: the throughput we got

torch.compile recompiled our SDXL UNet 38 times in production

LLM-as-judge variance broke our DPO training signal for 3 weeks

The bf16 grad accumulator that killed our SDXL LoRA training

I Built a Diagnostic Toolkit for PyTorch Because I Was Tired of Guessing Why Models Fail

Why Your PyTorch Training Crawls on a Beefy GPU (And How to Fix It)

VLM-scored calibration sets for INT8 quantisation, routed through Bifrost

Prefix caching in vLLM under multi-tenant agent traffic

Why your diffusion model is slow at batch size 1 (and what actually helps)

Your PyTorch Model File Can Execute Arbitrary Code — Here's How I Built a Scanner to Detect It

Distilling SAM 2 into a 6MB student for industrial inspection

My high-res image-to-video kept OOMing — turns out I was decoding outside no_grad