Skip to content

Forem

# gpu

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

soy

Apr 14

LLM Auto-Tunes llama.cpp, SASS Latency Analysis, DLSS Frame Gen for RTX 40

#gpu #nvidia #hardware

3 min read

plasmon

Apr 14

VRAMを増やせば解決する、は物理的に間違っている — HBM・CXL・Unified Memoryが取れなかったもの

#llm #gpu #vram

4 min read

plasmon

Apr 14

llama.cppの設定で8GBの性能が5倍変わる — 主要オプションの最適値を出した

#llm #llamacpp #gpu

4 min read

Apr 13

One Query, Four GPUs: Tracing a Distributed Training Stall Across Nodes

#gpu #ebpf #distributedcomputing

7 min read

Cover image for Task Manager is lying about your GPU temps. Here is how to read the real data in Python

Yaroslav Pristupa

Apr 13

Task Manager is lying about your GPU temps. Here is how to read the real data in Python

#ai #hardware #softwaredevelopment #gpu

4 min read

Cover image for AMD ML Complete Stack

Apr 12

AMD ML Complete Stack

#gpu #cpu #ai #llm

1 min read

soy

Apr 11

RTX 5090 cuBLAS Bug, Neural Texture Compression, Multi-GPU vLLM Inference

#gpu #nvidia #hardware

3 min read

soy

Apr 10

CUDA SGEMM Bug on RTX 5090, Kernel-Fusing for SGEMV, & Radeon RX 9070 XT Price Surge

#gpu #nvidia #hardware

4 min read

Rost

Apr 10

TGI - Text Generation Inference - Install, Config, Troubleshoot

#docker #gpu #observability #selfhosting

9 min read

Apr 9

Memory Coalescing: Same computation, 6x Performance Difference

#cuda #gpu #aiops #cpp

6 min read

soy

Apr 9

LLM GPU Breakthroughs: RT Cores, Llama.cpp Parallelism, AMD Optimizations

#gpu #nvidia #hardware

3 min read

Cover image for How to Train a 100B+ Parameter Model When You Can't Afford a GPU Cluster

Alan West

Apr 9

How to Train a 100B+ Parameter Model When You Can't Afford a GPU Cluster

#machinelearning #deeplearning #python #gpu

5 min read

Cover image for How K-Means Clustering Works (Explained by Extracting Colors from Images)

Francesco Di Donato

Apr 9

How K-Means Clustering Works (Explained by Extracting Colors from Images)

#webgl #machinelearning #javascript #gpu

3 min read

Apr 8

How I Stopped GGUF Models From Crashing My GPU: A Pre-flight VRAM Check

#localllm #gpu #machinelearning #python

4 min read

plasmon

Apr 8

99.8% of LLM Inference Power Isn't Spent on Computation

#llm #gpu #hardware #ai

7 min read

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