LLM inference
3 posts
Article
It walks through the handshake between your apps
Fireworks trained Ember-1 to cut Kimi K3's reasoning tokens by 35 to 50% without losing accuracy, aimed at agentic coding where reasoning is the cost.
Article
What Cerebras does to the weights it serves
Cerebras quantizes model weights only at storage and runs no pruning on its Shared Inference tier, and promises stable model IDs you can pin to.
Article
The 150x model tax
How inference techniques either move an LLM deployment along the latency-throughput frontier or push the whole frontier outward.