CommunityNews
Real-time LLM Inference on Standard Datacenter GPUs (3,000 tokens/s per request)
Today, Kog AI launches a tech preview of the Kog Inference Engine (KIE): 3,000 output tokens/s per request on 8× AMD MI300X GPUs and 2,100 on 8× NVIDIA H200 (FP16, no speculative decoding). This preview runs a 2B model, with support for large third-party MoE models coming next at similar speeds.
Read in full here:
https://blog.kog.ai/real-time-llm-inference-on-standard-gpus-3-000-tokens-s-per-request/
Popular Ai topics
In response to a national and international awakening on the issues of anti-Blackness and systemic discrimination, we have penned this pi...
New
SOME OF THE most dazzling recent advances in artificial intelligence have come thanks to resources only available at big tech companies, ...
New
Within the decade, Google aims to build a useful, error-corrected quantum computer. This will accelerate solutions for some of the world’...
New
Getting a glimpse into Nvidia’s R&D has become a regular feature of the spring GTC conference with Bill Dally, chief scientist and se...
New
New
Google’s Veo 3 delivers AI videos of realistic people with sound and music. We put it to the test.
New
I run Claude Code with --dangerously-skip-permissions flag, giving it full system access. Let me show you a new way of approaching comput...
New
From fear to optimism: why I am convinced AI is worth embracing.
New
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing rout...
New
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to ...
New
Other popular topics
Reading something? Working on something? Planning something? Changing jobs even!?
If you’re up for sharing, please let us know what you’...
New
Rust is an exciting new programming language combining the power of C with memory safety, fearless concurrency, and productivity boosters...
New
New
I ended up cancelling my Moonlander order as I think it’s just going to be a bit too bulky for me.
I think the Planck and the Preonic (o...
New
Oh just spent so much time on this to discover now that RancherOS is in end of life but Rancher is refusing to mark the Github repo as su...
New
Hello everyone! This thread is to tell you about what authors from The Pragmatic Bookshelf are writing on Medium.
New
A few weeks ago I started using Warp a terminal written in rust. Though in it’s current state of development there are a few caveats (tab...
New
This is going to be a long an frequently posted thread.
While talking to a friend of mine who has taken data structure and algorithm cou...
New
There appears to have been an update that has changed the terminology for what has previously been known as the Taskbar Overflow - this h...
New
Develop, deploy, and debug BEAM applications using BEAMOps: a new paradigm that focuses on scalability, fault tolerance, and owning each ...
New
Categories:
Sub Categories:
Popular Portals
- /elixir
- /rust
- /wasm
- /ruby
- /erlang
- /phoenix
- /keyboards
- /python
- /js
- /rails
- /security
- /go
- /swift
- /vim
- /clojure
- /java
- /emacs
- /haskell
- /typescript
- /svelte
- /onivim
- /kotlin
- /c-plus-plus
- /crystal
- /tailwind
- /react
- /gleam
- /ocaml
- /elm
- /flutter
- /vscode
- /ash
- /html
- /deepseek
- /zig
- /opensuse
- /centos
- /php
- /scala
- /react-native
- /lisp
- /sublime-text
- /textmate
- /nixos
- /debian
- /agda
- /deno
- /django
- /kubuntu
- /arch-linux
- /nodejs
- /spring
- /ubuntu
- /revery
- /manjaro
- /lua
- /julia
- /diversity
- /quarkus
- /markdown









