Skip to main content
Scour
Discover
Docs
Login
Sign Up
Discover
About
Docs
Changelog
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
GPUs
🎮 GPUs
GPU, graphics processing unit, parallel computing, hardware
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
279
posts in
13.0
ms
⚡
Parallel Computing
GitHub
·
1d
1 day ago
Running a 35B MoE model on a 2017 AMD RX 580 8GB via Vulkan (no
ROCm/CUDA
)
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Running a 35B MoE model on a 2017 AMD RX 580 8GB via Vulkan (no ROCm/CUDA)
🌐
Distributed Systems
jimmysong.io
·
4d
4 days ago
Why
GPUs
Became the Foundation of AI: A GPU Primer for K8s Veterans
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why GPUs Became the Foundation of AI: A GPU Primer for K8s Veterans
⚡
CUDA
Phoronix
·
9h
9 hours ago
Early AMD GCN
GPUs
Seeing Improved GPU Recovery - Another Valve-Led Linux Improvement
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Early AMD GCN GPUs Seeing Improved GPU Recovery - Another Valve-Led Linux Improvement
🎯
Memory Coalescing
XDA
·
1d
1 day ago
VRAM
was the only spec that decided which old
GPUs
actually survived
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for VRAM was the only spec that decided which old GPUs actually survived
⚡
Parallel Computing
kaggle.com
·
21h
21 hours ago
QLoRA: Fine-Tuning a 7B Model on a 16GB
GPU
(It Shrank to 5.4GB in Front of Me)
Discussed on
DEV
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)
⚡
CUDA
arxiv.org
·
6d
6 days ago
From Tokens to Regions:
CUDA-Sensitive
Instruction Tuning for
GPU
Kernel Generation
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation
⚡
CUDA
blog.guillaume-gomez.fr
·
2d
2 days ago
sysinfo: Getting
GPUs
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for sysinfo: Getting GPUs
⚡
Parallel Computing
Tom's Hardware
·
19h
19 hours ago
Open-source Vulkan driver NVK gains experimental DLSS support
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Open-source Vulkan driver NVK gains experimental DLSS support
🎯
Memory Coalescing
medium.com
·
2d
2 days ago
Why One
GPU
Isn’t Enough: What Happens When the Model No Longer Fits
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why One GPU Isn’t Enough: What Happens When the Model No Longer Fits
⚡
CUDA
Red Hat Emerging Technologies
·
4d
4 days ago
Triton Kernel Profiling with Proton and
ROCm
on AMD
GPUs
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Triton Kernel Profiling with Proton and ROCm on AMD GPUs
⚡
Parallel Computing
arxiv.org
·
6d
6 days ago
Fearless Concurrency on the
GPU
Covered by
4 sources
See all sources covering this story
including
GitHub
,
indiehacker.news
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Fearless Concurrency on the GPU
⚡
CUDA
TweakTown
·
2d
2 days ago
AMD plans to increase the price of its
graphics
cards by 10-15% in the second half of 2026
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AMD plans to increase the price of its graphics cards by 10-15% in the second half of 2026
⚡
CUDA
New Atlas
·
2d
2 days ago
Nvidia RTX Spark platform is AI workhorse first, gamer's friend second
Covers
NVIDIA and Microsoft Reinvent Windows PCs for the Age of Personal AI
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Nvidia RTX Spark platform is AI workhorse first, gamer's friend second
💾
Cache Coherence
thefrontierlab.ai
·
4d
4 days ago
Six months on the Strix Halo chip AMD now markets as "first-class
ROCm
"
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Six months on the Strix Halo chip AMD now markets as "first-class ROCm"
⚡
CUDA
fitservers.com
·
2d
2 days ago
The Complete Guide to Deploying DeepSeek R1 on a Dedicated Server
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The Complete Guide to Deploying DeepSeek R1 on a Dedicated Server
⚡
Parallel Computing
digitalocean.com
·
3d
3 days ago
Efficient LLM Compression with SparseGPT and Wanda on
GPU
Cloud
Covers
NVIDIA Triton Inference Server — NVIDIA Triton Inference Server
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Efficient LLM Compression with SparseGPT and Wanda on GPU Cloud
🎮
Game Engine Architecture
The Eclectic Light Company
·
2d
2 days ago
Explainer: Memory
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Explainer: Memory
🎯
Memory Coalescing
AnandTech Forums
·
6d
6 days ago
Will NPUs soon become useless silicon? — Windows 11’s Local AI is getting
GPU
support
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Will NPUs soon become useless silicon? — Windows 11’s Local AI is getting GPU support
⚡
Parallel Computing
kaggle.com
·
21h
21 hours ago
LoRA: I Trained <1% of a 1.5B Model and Matched a Full Fine-Tune
Discussed on
DEV
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for LoRA: I Trained <1% of a 1.5B Model and Matched a Full Fine-Tune
⚡
Parallel Computing
lemmy.world
·
1d
1 day ago
Wrote up a full guide for running AI locally on Windows (LM Studio + Ollama + Open WebUI)
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Wrote up a full guide for running AI locally on Windows (LM Studio + Ollama + Open WebUI)
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report