CentML Joins Google Cloud’s Springboard Program
May 8, 2025
Accelerating AI Optimization for Enterprise Customers
Blog
All
Updates
LlamaGuard Now Available on the CentML Platform
Apr 29, 2025
CentML welcomes three new members to the Llama herd
Case Studies
CentML provides Frode.ai with secure, GDPR-compliant inference
Updates
CentML is a Great Place to Work
Apr 22, 2025
Building a Team that Powers Innovation
Updates
Welcome to the Team, AI Agents
Apr 10, 2025
Enterprise growth now means building with AI, not just hiring.
Guides
Learn how we automated the search and get our top sessions for GTC 2025!
Guides
Discover how CentML optimized DeepSeek-R1 AWQ for record-breaking inference speed using Hidet
Updates
CentML is proud to announce our participation in the UTE Startup Perks program
Updates
Since the release of DeepSeek-R1, the open-source community has been working to optimize its inference speed. While low-level GPU optimizations have improved performance, CentML took it a step further using speculative decoding. By repurposing DeepSeek’s MTP module and implementing EAGLE-style recursive generation, we achieved a 2x speedup, generating up to 70 tokens/second.
Guides
AI inference forms the foundation of modern AI applications, transforming trained models into tools for actionable insight and real-world solutions. […]
Guides
The Basics of LLM Training
Nov 22, 2024
As AI progresses at a blazing pace, LLMs have emerged as a go-to tool for text generation, from code to […]
