Inference

Feeds to Scour
SubscribedAll
Scoured 338 posts in 6.8 ms

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

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

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

 🧠LLMs  Content type: Blog
medium.com
·

Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA

 🗄️Vector Databases
everylocalai.com··DEV

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

 📐Embeddings  Content type: Academic
arxiv.org·

Xiaomi MiMo-V2.5-Pro Just Hit 1,000 Tokens Per Second!

 🤖AI Agents
gizchina.com·

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

 🔌MCP
zozo123.github.io··Hacker News

Speculators v0.5.0: DFlash support and online training

 🎛️Fine-tuning
developers.redhat.com·

Big Blue’s Redbook on Storage Scale KV Cache management

 🤖AI Agents  Content type: News
blocksandfiles.com·

What Ollama Reveals About Local AI, Agents, and Open Models

 🌐World Models  Content type: Blog
odsc.medium.com·

I've tested so many desktop AI tools, but Hermes with Ollama is my new favorite - here's why

 🤖AI Agents  Content type: News  Content type: Tutorial
zdnet.com·

China's Xiaomi MiMo Is Now 15X Faster Than ChatGPT and Claude (4 minute read)

 🎛️Fine-tuning  Content type: News
decrypt.co·

Improved performance and model support with GGUF

 🧠LLMs  Content type: Blog
ollama.com·

Anatomy of a high-performance EP kernel

 🔌MCP  Content type: Blog
fergusfinn.com··Hacker News

Ollama 0.30 delivers faster NVIDIA GPU performance and wider hardware support

 🧠LLMs
alternativeto.net·

DiffusionGemma: The Developer Guide

 🎛️Fine-tuning  Content type: Blog
developers.googleblog.com·

Running LLM Inference on Kubernetes: What It Actually Takes

 🧠LLMs  Content type: Blog
fairwinds.com·

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

 🎛️Fine-tuning  Content type: News

Google's new open model DiffusionGemma generates text from noise instead of word by word

 🧠LLMs
the-decoder.com
·

NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI

 👁️Multimodal AI  Content type: Blog
blogs.nvidia.com·

NexusOS v2.0 – A zero-dependency pipeline streaming server chaos to Parquet

 🎛️Fine-tuning

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