OneTriangle

Inference engine that cuts LLM inference costs and latency by 20% using KV cache transfer between a small prefill model and a large decode model.

onetriangle.ai

Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.

About

OneTriangle runs prefill on a smaller model and decode on a larger one, transferring per-layer key/value tensors projected into the target model's attention space. This eliminates the cost of large-model prefill on long inputs, which typically dominates inference bills. The system gates each model pair on quality and latency thresholds and falls back to standard prefill when a pair does not meet them. It supports open-weight models including Llama, Qwen, Mistral, Gemma, and DeepSeek, with OneTriangle managing the GPU infrastructure. OneTriangle is a product of OneTriangle.

Added via
web
Ownership
unclaimed

Where to go

Product details

Product kind
Api
Open source
No
api
reduce LLM inference costsreduce inference latencyserve open-weight modelsKV cache-optimized inference
LlamaQwenMistralGemmaDeepSeek