DEV Community

#gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
2B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

2B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

5
Comments
15 min read
GPUs for AI in 2026: NVIDIA, AMD, Intel Compared

GPUs for AI in 2026: NVIDIA, AMD, Intel Compared

Comments
9 min read
Vulkan Computing with FP16 on PS4 GPU

Vulkan Computing with FP16 on PS4 GPU

Comments
1 min read
Running Multiple ComfyUI Instances in Parallel on a Single GPU — What Actually Breaks First

Running Multiple ComfyUI Instances in Parallel on a Single GPU — What Actually Breaks First

Comments
14 min read
Linux 7.2 Improves Multi-GPU Displays, M3 Support, Mesa Rusticl Defaults Arm Mali

Linux 7.2 Improves Multi-GPU Displays, M3 Support, Mesa Rusticl Defaults Arm Mali

Comments
3 min read
Does a Second GPU Increase Ollama's Context Window? (Quadro P2000 + RTX 3090 Tested)

Does a Second GPU Increase Ollama's Context Window? (Quadro P2000 + RTX 3090 Tested)

Comments
3 min read
LLM Inference Latency: Why Your 7B Model Gets 15 tok/s on a T4 but 3,500 tok/s on an H100

LLM Inference Latency: Why Your 7B Model Gets 15 tok/s on a T4 but 3,500 tok/s on an H100

2
Comments 1
5 min read
Bitluni's 8,192-Core DIY GPU Is Built From 13-Cent RISC-V Chips

Bitluni's 8,192-Core DIY GPU Is Built From 13-Cent RISC-V Chips

Comments
2 min read
CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?

CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?

1
Comments
4 min read
The KV cache, why LLM inference is memory-bound, not compute-bound

The KV cache, why LLM inference is memory-bound, not compute-bound

Comments
4 min read
The GPU Utilization Number That's Quietly Wrecking AI Team Budgets

The GPU Utilization Number That's Quietly Wrecking AI Team Budgets

Comments
5 min read
DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc

DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc

Comments
3 min read
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)

Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)

1
Comments
4 min read
Per-agent GPU cost: what LangSmith can't tell you

Per-agent GPU cost: what LangSmith can't tell you

Comments 1
4 min read
Managing Non-Homogeneous GPU and Resource Configurations in Ray Cluster IaC with Python-Based Solutions

Managing Non-Homogeneous GPU and Resource Configurations in Ray Cluster IaC with Python-Based Solutions

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