SlimServe Open-Sourced: Runs DeepSeek at 1k tok/s on 4x A100s

QuixiAI · x · 2026-08-11

QuixiAI has open-sourced SlimServe, an inference serving framework, demonstrating impressive concurrency capabilities.

When running the DeepSeek v4 Flash 0731 model on 4x A100 GPUs, it achieved the following benchmarks:

The framework aims to provide a highly efficient solution for LLM deployment.

Original post →

More from Infra

Infra channel →