- May 19, 2026
- 5 min read
Accelerating Inference on Friendli Dedicated Endpoints with Draft-Model Speculative Decoding
Read full article
- June 6, 2026
- 5 min read
At What Scale Do Dedicated Endpoints Make Sense?
Crossover
Workload
Inference
- June 4, 2026
- 4 min read
Run NVIDIA's Most Powerful Open Reasoning Model on Day 0 — Nemotron 3 Ultra on FriendliAI
NVIDIA
Nemotron
Agentic AI
- June 4, 2026
- 4 min read
One Benchmark Is Not Enough to Choose Your Inference Provider
LLM Inference
Inference Benchmarking
Performance Optimization
- May 28, 2026
- 5 min read
Kimi K2.6 Meets FriendliAI: Frontier Agentic AI, Deployed in One Click
Moonshot AI
Inference
Dedicated Endpoints
- May 15, 2026
- 5 min read
What's So Special About DeepSeek V4? Find Out On FriendliAI
DeepSeek-V4
Inference
Dedicated Endpoints
- May 11, 2026
- 3 min read
FriendliAI Expands to San Francisco to Scale Frontier AI Inference for Open-Weight and Custom Models
Expansion
Growth
Scale
- May 7, 2026
- 5 min read
Gemma-4-31B-it API on FriendliAI: #1 Output Speed & Response Time
Gemma
Inference
Model APIs
- April 29, 2026
- 4 min read
Scale Beyond GPU Memory Limits with Host KV Cache for Dedicated Endpoints
KV Cache
Dedicated Endpoints
Long-Context Inference
- April 29, 2026
- 5 min read
NVIDIA Nemotron™ 3 Nano Omni, Day-0 on FriendliAI: Unified Multimodal Reasoning, at Peak Performance
NVIDIA
Nemotron