Feeds to Scour
SubscribedAll
Scoured 213 posts in 12.7 ms
KV Cache Optimization: 3x Faster LLM Inference on 24GB VRAM  🚀LLM Deployment
tildalice.io·6d
KV Cache and Flash Attention with interactive diagrams  ⚡Quantization
kvcache.cobanov.dev·9h·Hacker News
HSTU: How Meta Built a Trillion-Parameter Recommender That Actually Scales  🔍RAG
mlwhiz.com
·2d
Running PyTorch Models on Apple Silicon GPUs with the ExecuTorch MLX Delegate  🚀LLM Deployment
pytorch.org·2d·Hacker News
How LLM Inference Works  🧠LLMs
arpitbhayani.me·6d·Hacker News
Why Shrinking an AI Model Often Makes It More Useful  🏢LLM Adoption
siliconopera.com·20h
RAVE: Re-Allocating Visual Attention in Large Multimodal Models  🎯RLHF
arxiv.org·2d
ChatGPT passes classic Alan Turing benchmark as AI-human distinction narrows  🧠LLMs
independent.co.uk·13h
A primer on how large language model works  🧠LLMs
mayijie.substack.com·4d·Substack
Benchmarking llama.cpp's brand-new MTP support on Strix Halo  ⚡Quantization
calebcoffie.com·2d·Hacker News
Training a 22MB prompt injection classifier  🚀LLM Deployment
stackone.com·13h·Hacker News
Character consistency in AI comics: 3 tricks that beat LoRA training for me  🎯LLM Finetuning
comicory.com·6d·DEV
Classifier Context Rot: Monitor Performance Degrades with Context Length  💻Local AI
lesswrong.com·2d
AI can pass the Turing Test in live chats and appear more human than us. I am spooked now  🤖AI Agents
digitaltrends.com·16h
AI Paper Review: Language Models are Few-Shot Learners (GPT-3)  🧠LLMs
freecodecamp.org·2d
MegaTrain Full Precision Training of 100B+ Parameter LLMs on a Single GPU  🚀LLM Deployment
github.com·3d·Hacker News
Understanding KV Cache: The Hidden Memory Cost of Serving LLMs  🚀LLM Deployment
melchi.me·1d·Hacker News
The Hidden Currency of AI  💻Local AI
are-you-burning-tokens.vercel.app·14h·Hacker News
You can put a Softmax in front of CrossEntropyLoss. PyTorch won’t stop you. Here are 16 other architecture bugs it won’t catch.  🚀LLM Deployment
gaox.substack.com·3d·Substack
GitHub makes GPT-5.3-Codex the Copilot base model for enterprises  🛡️AI Safety
igorslab.de·2d

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