This Week's Trending
A paper presented at SOSP 2025 details how token-level scheduling helped one GPU serve multiple LLMs, reducing demand from 1,192 to 213 H...
New
This Month's Trending
TLDR: We’re releasing a throughput-optimized megakernel for tensor-parallel inference with Llama-70B on H100s. Our kernel can aggressivel...
New
This Year's Trending
Last Three Year's Trending
Trending Over Three Years
Get money off!
The Pragmatic Bookshelf
35% off any eBook
Manning Publications
45% off any item
The Pragmatic Studio
20% off any course
Simply use coupon code "devtalk.com" at checkout. Where applicable this coupon can be used for an many items and as many times as you like!
Filter by Type:
Popular Tags
- #apple
- #code
- #programming
- #linux
- #web
- #blog-post
- #podcasts
- #video
- #news
- #otp
- #community
- #chatgpt
- #macos
- #microsoft
- #openai
- #learning
- #new
- #github
- #development
- #design
- #database
- #ios
- #project
- #performance
- #testing
- #internet
- #css
- #manning
- #android
- #apps
- #quantum
- #hardware
- #guide
- #ai
- #nvidia
- #intel
- #browser
- #amazon
- #liveview
- #privacy
- #blog
- #musk
- #llm
- #social
- #writing
- #games
- #windows
- #api
Popular Portals
- /elixir
- /rust
- /ruby
- /wasm
- /erlang
- /phoenix
- /keyboards
- /rails
- /python
- /js
- /security
- /go
- /swift
- /vim
- /clojure
- /haskell
- /emacs
- /java
- /svelte
- /onivim
- /typescript
- /kotlin
- /crystal
- /c-plus-plus
- /tailwind
- /react
- /gleam
- /ocaml
- /flutter
- /elm
- /vscode
- /ash
- /opensuse
- /html
- /centos
- /php
- /deepseek
- /zig
- /scala
- /textmate
- /lisp
- /sublime-text
- /react-native
- /debian
- /nixos
- /agda
- /kubuntu
- /arch-linux
- /django
- /ubuntu






