ML Inference

inference engine, model serving, inference optimization, runtime

Feeds to Scour
SubscribedAll
Scoured 148 posts in 19.8 ms

I Processed 2.4 Billion Tokens Across 52 AI Models for $0.52. Here's the Full Breakdown.

 🔄MLOps
saintlex.sbs··DEV

How we fight GPU scarcity without compromise

 🧠Deep Learning  Content type: Blog
equixly.com··Hacker News

Real-Time Industrial Defect Detection on Edge Hardware Using Fine-Tuned YOLOv8: A Systematic Benchmark on the NEU Surface Defect Database and MVTec AD with Automotive & Battery Manufacturing Extensions

 🖥️Systems ML  Content type: Academic
arxiv.org·

KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++

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

OpenCV 5 release - New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations - CNX Software

 🧠Deep Learning  Content type: News
cnx-software.com·

Why agentic AI needs an open inference stack

 🔄MLOps
redhat.com·

CoreML vs TFLite: iPhone 15 Pro GPU 2.3x Faster

 🤖Machine Learning  Content type: Blog  Content type: Discussion
tildalice.io·

Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good

 🗜️Quantization  Content type: Blog
towardsai.net·

How Will the Chiplet IC Market Transform Semiconductor Design Through 2034?

 🎮GPU Programming  Content type: Blog

End-to-End Context Compression at Scale

 📐Model Architecture  Content type: Academic
arxiv.org·

How frontier teams are reinventing AI-native development

 🔄MLOps  Content type: Blog
aws.amazon.com·

[AINews] FrontierCode: Benchmarking for Code Quality over Slop

 🗜️Quantization  Content type: News
latent.space
·

Model Evaluations: Prove Your Routing Policy Actually Works

 ⚙️Model Training  Content type: Blog
digitalocean.com·

Learning Fuzzy Logic: Automatic Rule Discovery Through Differentiable Circuits

 🤖Machine Learning
metafunctor.com··DEV

A 185 TOPS/W/mm2 Bayesian Inference Engine with 640 aJ Write-Free FeFET GRNG for Uncertainty-Aware Aerial Search and Rescue

 🧠Deep Learning  Content type: Academic
arxiv.org·

huawei-csl/KVarN: KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

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

ASUS ExpertBook Ultra Flagship Business Laptop Debuts In SEA Markets, Featuring Sub-1kg Chassis & Intel Core Ultra X7 Processor

 🦀WGPU
pokde.net·

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

 🖥️Systems ML  Content type: Academic
arxiv.org·

Understanding Agentic AI Infrastructure

 🔄MLOps  Content type: Blog
mirantis.com·

How to Run Gemma 4 12B Locally - The Best AI For Consumer Laptops

 🔄MLOps  Content type: Video
youtube.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