DEV Community

#gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Shipping Ming-Image Design: size the card by its files, and check the alpha in code

Shipping Ming-Image Design: size the card by its files, and check the alpha in code

Comments
4 min read
I Ran Whisper on a 24 GB GPU for 30 Days. It Used 8.

I Ran Whisper on a 24 GB GPU for 30 Days. It Used 8.

Comments
6 min read
How much VRAM do popular LLMs really need at 4-bit and 8K context? Data from 26 models

How much VRAM do popular LLMs really need at 4-bit and 8K context? Data from 26 models

Comments 1
6 min read
How Does Rust Code Run on a GPU? Tracing cuda-oxide and PTX

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

Comments
10 min read
H100 NVL

H100 NVL

Comments
7 min read
Serving a 1B math model on vLLM: the memory cap sets how many answers fit, not how fast

Serving a 1B math model on vLLM: the memory cap sets how many answers fit, not how fast

Comments
4 min read
Как я впихивал три модели в 6 ГБ видеопамяти

Как я впихивал три модели в 6 ГБ видеопамяти

2
Comments 1
2 min read
LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper

LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper

Comments
5 min read
How I squeezed three models into 6 GB of VRAM

How I squeezed three models into 6 GB of VRAM

2
Comments 2
6 min read
Fitting Flint's coding agent on a 24 GB RTX 4090: context is the knob that decides

Fitting Flint's coding agent on a 24 GB RTX 4090: context is the knob that decides

Comments
5 min read
When Java 27 Removed JVMCI, TornadoVM Built Its Own Compiler

When Java 27 Removed JVMCI, TornadoVM Built Its Own Compiler

1
Comments
8 min read
GPU Info Processing Caused Performance Regression: Root Cause Identified and Resolved

GPU Info Processing Caused Performance Regression: Root Cause Identified and Resolved

Comments
11 min read
TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.

TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.

Comments
5 min read
DePIN GPU Bubble Bursts: Render, Akash Utilization Slide Below 40% as Hyperscaler Prices Collapse

DePIN GPU Bubble Bursts: Render, Akash Utilization Slide Below 40% as Hyperscaler Prices Collapse

Comments
4 min read
Running neural networks in a Unity editor tool with compute shaders

Running neural networks in a Unity editor tool with compute shaders

1
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.