Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Real-time AI Systems
⚡ Real-time AI Systems
Stream Processing, Low Latency, Event Processing, Online Learning
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
21
posts in
6.0
ms
How ERGO Hestia reduced
time-to-market
with Lakebase and Mosaic
AI
Model
Serving
🔧
Systems-level optimizations for LLM serving
Content type:
Blog
databricks.com
·
3h
3 hours ago
Actions for How ERGO Hestia reduced time-to-market with Lakebase and Mosaic AI Model Serving
The Hidden Tax Killing Your ML Team’s Velocity – And the Architecture Decision That Fixes It
🔧
Systems-level optimizations for LLM serving
Content type:
Blog
medium.com
·
6d
6 days ago
Actions for The Hidden Tax Killing Your ML Team’s Velocity – And the Architecture Decision That Fixes It
When your data
model
is the bottleneck: lessons from Medium’s
feature
store
🔍
Retrieval-augmented generation
thenewstack.io
·
2d
2 days ago
Actions for When your data model is the bottleneck: lessons from Medium’s feature store
Real-time
fraud
detection
for financial transactions
🔍
Retrieval-augmented generation
Content type:
Blog
redis.io
·
23h
23 hours ago
Actions for Real-time fraud detection for financial transactions
Introducing
Streamling
: Performant and Extensible Data
Streaming
Framework
🔧
Systems-level optimizations for LLM serving
Content type:
News
streamingdata.tech
·
2d
2 days ago
Actions for Introducing Streamling: Performant and Extensible Data Streaming Framework
Our first customers were the exception
💬
Prompt optimizations for LLM serving
Content type:
Blog
apurvamehta.com
·
6d
6 days ago
·
Hacker News
Actions for Our first customers were the exception
When
Event
Time
Meets
Reality
: Lessons from Building Billing on Apache Flink (12 minute read)
⚙️
AI Infrastructure Automation
Content type:
Blog
medium.com
·
22h
22 hours ago
Actions for When Event Time Meets Reality: Lessons from Building Billing on Apache Flink (12 minute read)
Deploy ADX Business on DigitalOcean
⚙️
AI Infrastructure Automation
digitalocean.com
·
1d
1 day ago
Actions for Deploy ADX Business on DigitalOcean
How We Built a Rolling-Window
Feature
Store
for Telecom Churn Prediction at Scale
🔧
Systems-level optimizations for LLM serving
Content type:
Blog
medium.com
·
17h
17 hours ago
Actions for How We Built a Rolling-Window Feature Store for Telecom Churn Prediction at Scale
TRADE: Transducer-Augmented Decoder for Speech LLM
🔧
Systems-level optimizations for LLM serving
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for TRADE: Transducer-Augmented Decoder for Speech LLM
Code was the easy part all along. What's next for Open Source?
⚙️
AI Infrastructure Automation
Content type:
Blog
lopez.fi
·
22h
22 hours ago
·
Hacker News
Actions for Code was the easy part all along. What's next for Open Source?
Predicting the World Cup Winner: Live Coding with Hopswor...
🧠
Large Language Models (LLMs)
hopsworks.ai
·
1d
1 day ago
·
Hacker News
Actions for Predicting the World Cup Winner: Live Coding with Hopswor...
Particle: Google Launches Gemini 3.5 Live Translate for Continuous Voice Translation
🧠
Large Language Models (LLMs)
Content type:
News
particle.news
·
2d
2 days ago
Actions for Particle: Google Launches Gemini 3.5 Live Translate for Continuous Voice Translation
Cerebras shares climb as Wall Street brokerages back
AI
chip strategy
📊
AI Performance Profiling
channelnewsasia.com
·
3d
3 days ago
Actions for Cerebras shares climb as Wall Street brokerages back AI chip strategy
Tejas-TA/predikit: The missing bridge between your ML
models
and your
AI
agents.
🤖
Agents using LLMs
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for Tejas-TA/predikit: The missing bridge between your ML models and your AI agents.
Two Leaps to 1000 Tokens/s on a 1T-Parameter
Model
: On
Inference
Systems
, Execution Boundaries, and Co-Design
📊
AI Performance Profiling
Content type:
Blog
tilert.ai
·
3d
3 days ago
·
Hacker News
Actions for Two Leaps to 1000 Tokens/s on a 1T-Parameter Model: On Inference Systems, Execution Boundaries, and Co-Design
How Will the
AI
IC Market Evolve Amid Rising Artificial Intelligence Adoption Through 2034?
⚙️
AI Infrastructure Automation
Content type:
Blog
semiconinsights.blogspot.com
·
1d
1 day ago
Actions for How Will the AI IC Market Evolve Amid Rising Artificial Intelligence Adoption Through 2034?
Less-relevant results
Benchmarking dots.tts on Strix Halo
🧠
Large Language Models (LLMs)
sleepingrobots.com
·
3d
3 days ago
Actions for Benchmarking dots.tts on Strix Halo
Upstart chipmakers keep challenging Nvidia. This
time
it's Microsoft-backed D-Matrix
📊
AI Performance Profiling
Content type:
News
cnbc.com
·
2d
2 days ago
·
Hacker News
Actions for Upstart chipmakers keep challenging Nvidia. This time it's Microsoft-backed D-Matrix
Agent Memory Database: Build It on TiDB with SQL and Python
🔍
Retrieval-augmented generation
Content type:
Blog
pingcap.com
·
1d
1 day ago
Actions for Agent Memory Database: Build It on TiDB with SQL and Python
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
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
Browse
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