LLM Internals

Feeds to Scour
SubscribedAll
Scoured 123 posts in 6.8 ms

Handshake: Partner-Specific Protein-Protein Binding Site Prediction at Scale Using ProstT5 and Cross-Chain Attention

 🔧Model Serving  Content type: Academic
biorxiv.org·

Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning

 🔧Model Serving  Content type: Academic
arxiv.org·

Issue #390 - The ML Engineer 🤖

 ⚙️C++  Content type: News  Content type: Blog

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

 🔧Model Serving  Content type: Academic
arxiv.org·

If Claude Fable stops helping you, you'll never know

 🔧Model Serving  Content type: Blog

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction

 🔧Model Serving  Content type: Academic
arxiv.org·

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

 🔧Model Serving

Local AI has a hardware accessibility problem, and the answer to it isn't RTX Spark

 🔧Model Serving
xda-developers.com·

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

 🔧Model Serving  Content type: Academic
arxiv.org·

harshuljain13/llm-inference-at-scale: A Practitioner handbook for production llm serving.

 🔧Model Serving  Content type: Code
github.com··Hacker News

Research Proposal: Decoupled RISC-LLM Architectures via Circadian Synaptic Consolidation

 🖥️Systems Programming
aermia.com··Hacker News

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

 🔧Model Serving  Content type: Blog
jimmysong.io·

Dynamic Linear Attention

 🔧Model Serving  Content type: Academic
arxiv.org·

How the AI Computing Paradigm Is Deconstructing Internet Governance

 🏗️System Design
circleid.com·

The data center construction boom has entered a new chapter

 Low Latency  Content type: News
consultancy-me.com·

Scale Robot Reinforcement Learning with NVIDIA Isaac Lab on Amazon SageMaker AI

 🔧Model Serving  Content type: Blog
aws.amazon.com·

DeepSeek V4, LeCun's Bet Against LLMs, and Lovable's Self-Improving Agent - The Tokenizer Edition #30

 🔧Model Serving

Causal Semantic Alignment for LLM-based Time Series Forecasting

 🔧Model Serving  Content type: Academic
arxiv.org·

Using local LLMs for agentic coding

 🔧Model Serving  Content type: Blog
blog.alexewerlof.com·

Connectivity Revolution or Evolution Inside Data Centers?

 Low Latency  Content type: News
eetimes.com·
Sign up or log in to see more results

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