Inference

Feeds to Scour
SubscribedAll
Scoured 347 posts in 8.7 ms

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

 🧠LLMs  Content type: Code
github.com··Hacker News

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

 🧠LLMs  Content type: News

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

 🧠LLMs  Content type: Blog
medium.com
·

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

 🧠LLMs  Content type: Academic
arxiv.org·

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

 🧠LLMs  Content type: Blog
dnhkng.github.io·

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

 🧠LLMs

LLM Inference Engineering Room — Part 3: The Orchestration Layer

 🧠LLMs  Content type: Blog

A system programmer’s guide to LLM inference

 🧠LLMs  Content type: Blog

Big Blue’s Redbook on Storage Scale KV Cache management

 🧠LLMs  Content type: News
blocksandfiles.com·

The hidden bottleneck in LLM inference and the impact on MLPerf benchmarking

 🧠LLMs
edn.com·

Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell

 🏆SOTA Models  Content type: News  Content type: Blog

Anatomy of a high-performance EP kernel

 🧠LLMs  Content type: Blog
fergusfinn.com·

lightmetal: GPU LLM Inference From a Single Java 25 JAR

 🧠LLMs  Content type: Blog
adambien.blog·

A visionary legacy: Andy Brown

 🕸️Distributed Systems
uk.themedialeader.com·

Nvidia DGX Spark GB10 – AI Models and Guide with vLLM and Autonomous Script

 🧠LLMs  Content type: Code
github.com··Hacker News

Two Leaps to 1000 Tokens/s on a 1T-Parameter Model: On Inference Systems, Execution Boundaries, and Co-Design

 🧠LLMs  Content type: Blog
tilert.ai··Hacker News

Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

 🎛️Fine-tuning

Running LLM Inference on Kubernetes: What It Actually Takes

 🧠LLMs  Content type: Blog
fairwinds.com·

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

 🧠LLMs  Content type: Blog

How we fight GPU scarcity without compromise

 🧠LLMs  Content type: Blog
equixly.com··Hacker News

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