LLMs

large language models, foundation models, LLM inference, transformers

Feeds to Scour
SubscribedAll
Scoured 323 posts in 7.9 ms

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

 Inference  Content type: Code
github.com··Hacker News

A system programmer’s guide to LLM inference

 Inference  Content type: Blog

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference

 Inference  Content type: Academic
arxiv.org·

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 Inference

lightmetal: GPU LLM Inference From a Single Java 25 JAR

 🌐Open Source AI  Content type: Blog
adambien.blog·

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 Inference  Content type: News

LLM Inference Engineering Room — Part 3: The Orchestration Layer

 Inference  Content type: Blog

Report: GKE Inference Gateway delivers up to 92% faster AI responses

 Inference  Content type: Blog

Modernizing attendance ticketing in SAS Viya using SAS Agentic AI Accelerator

 🤖AI Agents  Content type: Blog
blogs.sas.com·

Build a Medical Report Analyzer on Dedicated Inference with Python

 Inference
digitalocean.com·

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

 Inference  Content type: Blog
dnhkng.github.io·

Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models

 🌐Open Source AI
thehackernews.com·

LangChain Explained: Understanding Models, Prompts, Chains, Memory, Indexes, and Agents

 ✍️Prompt Engineering  Content type: Blog
towardsai.net·

My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs

 ✍️Prompt Engineering  Content type: News  Content type: Blog

How we fight GPU scarcity without compromise

 Inference  Content type: Blog
equixly.com··Hacker News

LLM Observability: What To Instrument and How To Act on It

 ✍️Prompt Engineering  Content type: Blog
blog.n8n.io·

Autonomous AI worm uses local models to exploit networks and repair its own code

 🌐Open Source AI
4sysops.com·

Running LLM Inference on Kubernetes: What It Actually Takes

 Inference  Content type: Blog
fairwinds.com·

Ask HN: Is software engineering still a good career choice for new students?

 Inference  Content type: Discussion

PagedAttention vs Traditional KV Cache: How vLLM Reinvented GPU Memory for LLM Inference

 Inference  Content type: Blog
medium.com
·

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