DEV Community

#gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The model was the easy part

The model was the easy part

Comments
7 min read
Running a dense 33B agent model on one 24 GB GPU: the offload trap and the empty reply

Running a dense 33B agent model on one 24 GB GPU: the offload trap and the empty reply

Comments
5 min read
Mitigating CVE-2026-47591: Fixing the 'NvRoot' GPU Local Privilege Escalation Vulnerability

Mitigating CVE-2026-47591: Fixing the 'NvRoot' GPU Local Privilege Escalation Vulnerability

Comments
7 min read
How I Built an LLM Inference Engine From Scratch in CUDA (235 tokens/s on a 6 GB Laptop GPU)

How I Built an LLM Inference Engine From Scratch in CUDA (235 tokens/s on a 6 GB Laptop GPU)

Comments
8 min read
How can you get free cloud GPUs for AI training?

How can you get free cloud GPUs for AI training?

Comments
8 min read
NVIDIA: From Gaming Graphics to the Engine of the AI Revolution

NVIDIA: From Gaming Graphics to the Engine of the AI Revolution

Comments
12 min read
What are the best Google Colab alternatives for training in 2026?

What are the best Google Colab alternatives for training in 2026?

Comments
9 min read
Leasing Nvidia: Por que as GPUs disparam e o que fazer agora

Leasing Nvidia: Por que as GPUs disparam e o que fazer agora

Comments
4 min read
Leasing de GPUs Nvidia: guĂ­a, impacto y script Python para vigilar precios

Leasing de GPUs Nvidia: guĂ­a, impacto y script Python para vigilar precios

Comments
4 min read
How do you keep training alive now that Runpod spot Pods are gone?

How do you keep training alive now that Runpod spot Pods are gone?

Comments
10 min read
How much GPU do you need to run an LLM locally? The rules of thumb we use

How much GPU do you need to run an LLM locally? The rules of thumb we use

Comments
4 min read
Clover-35B-A3B on llama.cpp: what "AR mode only" means, and a GGUF that answers in Gs

Clover-35B-A3B on llama.cpp: what "AR mode only" means, and a GGUF that answers in Gs

Comments
4 min read
Your CUDA Code Didn't Change. Your Risk Register Just Did: What Nvidia's CEO Exit Means for Builders

Your CUDA Code Didn't Change. Your Risk Register Just Did: What Nvidia's CEO Exit Means for Builders

Comments
4 min read
What are the best SaladCloud alternatives for GPU workloads?

What are the best SaladCloud alternatives for GPU workloads?

Comments
8 min read
How Many Closed Findings Before You Trust a Routing Change

How Many Closed Findings Before You Trust a Routing Change

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