GPU Memory

Feeds to Scour
SubscribedAll
Scoured 301 posts in 15.1 ms

Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

 🔌IOMMU
everylocalai.com··DEV

Nvidia RTX Spark Unreal Engine: GB10 Blackwell Laptop with 128GB Unified Memory

 🔷SPIR-V
armdevices.net·

SK Hynix bets HBM, wins Nvidia jackpot

 🎮GPU Scheduling
jonpeddie.com·

Massive AI Storage Demand Creates a New Memory Wall

 CPU Caches  Content type: News
eetimes.com·

Enhancing High Bandwidth Memory (HBM) Reliability With 3D X-ray Inspection

 🔌PCIe
semiengineering.com·

AMD Believes Unified Memory Architectures Open Up a "World of Possibilities", Will Shape Their Product Choices & Roadmaps In Future

 🔗IPC  Content type: News
wccftech.com·

NVIDIA chip powers local AI workloads

 🎮GPU Scheduling
edn.com·

2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP

 ⚙️Kernel Dev  Content type: Blog
dnhkng.github.io·

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

 🎮GPU Scheduling  Content type: Code
github.com··Hacker News

GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)

 🗜️Compression Algorithms

Tech leaker claims that the RTX 50 Super refresh is still on, despite the RAMpocalypse, and it'll be joined by a 12 GB RTX 5060

 🔌PCIe  Content type: News
pcgamer.com
·

Nvidia RTX Spark: The $2,900 Floor Tells You Everything

 🎮GPU Scheduling  Content type: Blog  Content type: Discussion
tildalice.io·

High Bandwidth Flash | A New Memory for AI Data Centers and Edge Computing | Sandisk

 ✍️Write Amplification
ncnonline.net·

GMKtec EVO-X3 mini PC is coming with OCuLink support and a Ryzen AI MAX+ PRO 495 variant packing 192GB of memory

 🔌PCIe  Content type: News
tweaktown.com·

Re: Things that made you go "WTF?" today o_O

 🔄Memory Reclaim
bay12forums.com·

Nvidia GeForce RTX 50 Super GPUs may launch in early 2027 with 50% more VRAM

 🎮GPU Scheduling
club386.com·

NVIDIA's RTX 5060 May Finally Get The VRAM Upgrade Gamers Wanted

 🎮GPU Scheduling  Content type: News
hothardware.com·

Apple's most advanced on-device AI features will only work on select devices

 Storage Class Memory  Content type: News
gsmarena.com·

From GPU to Token: The 8-Layer Observability Stack for AI Infrastructure

 🎮GPU Scheduling  Content type: Blog
jimmysong.io·

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

 🔗IPC

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help